Mobile phone information privacy protection method and system based on big data analysis

Abstract

The application discloses a mobile phone information privacy protection method and system based on big data analysis, relates to the technical field of information security, and comprises the following steps: collecting the latest privacy protection requirements from an application market and / or a regulatory department, and extracting privacy protection clauses to generate a standardized privacy protection rule dataset; after obtaining an encryption analysis result, combining big data analysis to generate a dynamic privacy protection rule file; parsing the bytecode of a mobile phone application through an ASM framework for the dynamic privacy protection rule file, automatically modifying sensitive API calling points, and inserting privacy monitoring logic; repackaging the modified sensitive API calling points into an APK file, and verifying the privacy monitoring of the application program; and the application adopts encryption analysis and distributed training to ensure the safe sharing and processing of privacy data under the participation of multiple parties, effectively enhances the protection of mobile phone information privacy, and is suitable for complex and changeable application scenarios.

Description

Technical Field

[0001] The present invention relates to the field of information security technology, and in particular to a method and system for protecting mobile phone information privacy based on big data analysis. Background Art

[0002] With the widespread adoption of smartphones, the frequency of mobile application usage has increased significantly, and the collection and use of user personal information has become increasingly complex. To address the risk of privacy leakage, effectively protecting user privacy data has become a key area of ​​current technological research. Existing privacy protection technologies primarily rely on encryption, access control, and permission management to prevent the leakage of sensitive user information. However, with the explosive growth of data volumes and the diversification of user privacy needs, traditional privacy protection methods are struggling to address emerging privacy risks. For example, while permission-based privacy protection technologies can limit applications' access to user data to a certain extent, they cannot prevent the abuse of legitimate permissions or privacy leaks during data sharing. Furthermore, existing encryption technologies mostly rely on a single encryption algorithm and lack flexible adaptability to data usage scenarios. Especially in the big data environment, with the increasing demand for multi-party sharing and analysis of private data, existing technologies struggle to balance the contradiction between data availability and privacy protection.

[0003] Another shortcoming of existing technologies is the lag in the development and enforcement of privacy protection rules. Mobile app privacy protection terms and policies are typically defined by developers themselves, with long update cycles. Privacy protection regulations and standards are constantly evolving, making it difficult for privacy protection rules to keep up with the latest legal requirements. Furthermore, existing privacy protection mechanisms are mostly static rule-matching mechanisms, lacking the ability to dynamically adjust to increasingly complex application scenarios. For example, privacy monitoring systems typically rely on predefined rules to detect sensitive operations, but these rules are often rigid and cannot adapt to changes in user behavior and data flows in real time. Consequently, existing privacy protection technologies lack sufficient flexibility and intelligent support to address complex and ever-changing privacy risks. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a mobile phone information privacy protection method based on big data analysis to solve the problems of hysteresis and static nature of existing privacy protection rules.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for protecting mobile phone information privacy based on big data analysis, which includes collecting the latest privacy protection requirements from application markets and / or regulatory authorities, extracting privacy protection clauses, and generating a standardized privacy protection rule dataset;

[0008] Based on the privacy-preserving rule dataset, distributed training and encrypted aggregation are used to generate global model parameters;

[0009] For global model parameters, multi-party secure computing is used to encrypt and analyze the privacy data of mobile applications;

[0010] After obtaining the encryption analysis results, a dynamic privacy protection rule file is generated in combination with big data analysis;

[0011] For dynamic privacy protection rule files, the ASM framework is used to parse the bytecode of mobile applications, automatically modify sensitive API call points, and insert privacy monitoring logic;

[0012] Repackage the modified sensitive API call points into an APK file and perform privacy monitoring and verification on the application.

[0013] As a preferred solution of the mobile phone information privacy protection method based on big data analysis described in the present invention, wherein: the said collecting the latest privacy protection requirements from the application market and / or regulatory authorities, extracting privacy protection terms, and generating a standardized privacy protection rule data set, the specific steps are as follows:

[0014] Automatically obtain the latest privacy protection requirements from app markets and / or regulatory authorities through public APIs and web crawlers. Privacy protection requirements include privacy protection terms and policies.

[0015] Based on the obtained privacy protection requirements, use NLP methods to clean up the noise data in the private text;

[0016] Use the pre-trained legal domain BERT model to perform named entity recognition on the cleaned privacy text and extract privacy protection clauses;

[0017] According to the privacy protection standards, the extracted privacy protection clauses are mapped to the clause framework to unify the format;

[0018] Based on the unified format of the clause framework, semantic similarity is used to match regulatory clauses described in different languages;

[0019] Standardize regulatory provisions from different sources through rule mapping and hierarchical classification;

[0020] Use rule engines and knowledge graphs to verify and check the consistency of standardized regulatory clauses to form a standardized privacy protection rule dataset.

[0021] As a preferred solution of the mobile phone information privacy protection method based on big data analysis described in the present invention, wherein: based on the privacy protection rule data set, distributed training and encrypted aggregation are used to generate global model parameters. The specific steps are as follows:

[0022] Using a hierarchical federated learning architecture, the privacy-preserving rule dataset is grouped into different nodes and layers;

[0023] At each node in each layer, based on the respective data grouping, the model is trained using the local privacy rule dataset to obtain the model parameters of each layer;

[0024] Each node calculates the loss function based on the local privacy rule dataset and updates the model parameters of each layer by optimizing the loss function;

[0025] The updated model parameters of each layer are sent to the central server of that layer through encrypted communication, and multi-party secure computing is used to encrypt and aggregate the parameters within the layer to output the global model parameters. The expression is:

[0026] ;

[0027] in, Indicates in The global model parameters obtained after the round of training are Express The parameters of each node are weighted averaged. Indicates the total number of nodes, Indicates the The node in The local model parameters obtained after rounds of training, Indicates the round of iteration.

[0028] As a preferred solution of the mobile phone information privacy protection method based on big data analysis described in the present invention, wherein: the global model parameters are encrypted and analyzed by multi-party secure computing on the privacy data of mobile phone applications. The specific steps are as follows:

[0029] Through global model parameters, coordinate each node to perform local training without sharing original data, and update the global model parameters through encrypted aggregation summary nodes;

[0030] The updated global model parameters will be fed back to each node, and each node will collect local privacy data based on the updated global model parameters;

[0031] Normalize local privacy data into a unified feature scale;

[0032] Perform homomorphic encryption on the standardized local private data to generate an encrypted dataset;

[0033] Each node performs local model training based on its own encrypted dataset and calculates encrypted gradient data;

[0034] The encrypted gradient data is transmitted to the central server, and the encrypted gradient data of each node is aggregated through multi-party secure computing to obtain the global encrypted gradient data;

[0035] By combining the dynamic changes of the time dimension with the globally encrypted gradient data, the gradient descent model parameters are updated;

[0036] Feedback the updated gradient descent model parameters to each node, and each node uses the subkey to decrypt the global gradient descent model parameters;

[0037] The decrypted global gradient descent model parameters are combined with the encrypted gradient data of each node to generate encrypted analysis results.

[0038] As a preferred solution of the mobile phone information privacy protection method based on big data analysis described in the present invention, after obtaining the encryption analysis results, a dynamic privacy protection rule file is generated in combination with big data analysis. The specific steps are as follows:

[0039] The generated encryption analysis results and global model parameters are fed into the big data analysis engine to evaluate the performance of the global encryption gradient data;

[0040] The big data analysis engine performs privacy risk analysis based on the encryption analysis results;

[0041] The big data analysis engine generates privacy protection recommendations based on performance evaluation results and privacy risk analysis results using rule-based reasoning and machine learning models;

[0042] Based on the privacy risk analysis results and privacy protection recommendations, a dynamic privacy protection rule file is generated through a decision tree.

[0043] As a preferred solution of the mobile phone information privacy protection method based on big data analysis described in the present invention, the dynamic privacy protection rule file is parsed through the ASM framework to parse the bytecode of the mobile phone application, automatically modify the sensitive API call points, and insert the privacy monitoring logic. The specific steps are as follows:

[0044] Use apktool to decompile the APK and obtain the .dex file;

[0045] Use dex2jar to convert the .dex file into .class bytecode;

[0046] Use the ASM framework to parse the decompiled .class bytecode, and read the .class bytecode through ClassReader to generate the class structure tree of the file;

[0047] By rewriting the visitMethod method, all Java methods in the class structure tree are captured and processed, and a bytecode interceptor for each Java method is generated;

[0048] Combine dynamic privacy protection rule files and bytecode interceptors to automatically identify sensitive API call points in .class bytecodes;

[0049] At the identified sensitive API call points, the bytecode of the privacy monitoring method is inserted before the Java method call through ASM's MethodVisitor, and the result processing logic is inserted after the Java method call.

[0050] As a preferred solution of the mobile phone information privacy protection method based on big data analysis described in the present invention, the modified sensitive API call points are repackaged into an APK file, and the privacy monitoring verification of the application is performed. The specific steps are as follows:

[0051] Use the d8 tool to repackage the modified .class bytecode into a .dex file, replace the original .dex file, and generate a new .dex file;

[0052] Replace the new .dex file into the decompiled file structure and use apktool to repackage and generate a new APK file;

[0053] Use the developer key to sign the new APK file and install it on the smart terminal device;

[0054] Use automated testing tools to verify whether sensitive API call points trigger the inserted privacy monitoring logic;

[0055] If the inserted privacy monitoring logic is triggered, it means that the sensitive API call point is captured by the monitoring logic, relevant log records are generated, and privacy protection measures are executed;

[0056] If the inserted privacy monitoring logic is not triggered, it means that the sensitive API call point is not captured and the log lacks relevant information about the monitoring logic. Check the bytecode and modify and verify the test environment until the inserted privacy monitoring logic is successfully triggered.

[0057] In a second aspect, the present invention provides a mobile phone information privacy protection system based on big data analysis, comprising an information collection module, a global model parameter generation module, an encryption analysis module, a dynamic privacy protection rule file generation module, a bytecode modification module, and a verification module;

[0058] The information collection module is used to collect the latest privacy protection requirements from the application market and / or regulatory authorities, extract privacy protection clauses, and generate a standardized privacy protection rule dataset;

[0059] The global model parameter generation module generates global model parameters based on the privacy protection rule dataset using distributed training and encrypted aggregation;

[0060] The encryption analysis module is used to perform encryption analysis on the privacy data of mobile phone applications using multi-party secure computing on global model parameters;

[0061] The dynamic privacy protection rule file generation module is used to generate a dynamic privacy protection rule file in combination with big data analysis after obtaining the encryption analysis results;

[0062] The bytecode modification module is used to parse the bytecode of the mobile application through the ASM framework for the dynamic privacy protection rule file, automatically modify sensitive API call points, and insert privacy monitoring logic;

[0063] The verification module is used to repackage the modified sensitive API call points into an APK file and perform privacy monitoring verification on the application.

[0064] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the mobile phone information privacy protection method based on big data analysis as described in the first aspect of the present invention is implemented.

[0065] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the mobile phone information privacy protection method based on big data analysis as described in the first aspect of the present invention.

[0066] The beneficial effects of the present invention are as follows: by combining technologies such as big data analysis, federated learning and multi-party secure computing, the present invention can realize dynamic and real-time generation and updating of privacy protection rules, overcoming the problems of lag and static nature of privacy protection rules in the existing technology; secondly, it can keep up with the latest privacy protection regulations and standards in a timely manner, automatically modify sensitive API call points in applications, and improve the flexibility of privacy protection; in addition, the present invention adopts encryption analysis and distributed training to ensure the secure sharing and processing of privacy data with the participation of multiple parties, effectively enhancing the protection of mobile phone information privacy, and is suitable for complex and changeable application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0068] Figure 1 This is a flow chart of the mobile phone information privacy protection method based on big data analysis in Example 1.

[0069] Figure 2 This is a module diagram of the mobile phone information privacy protection method based on big data analysis in Example 1. DETAILED DESCRIPTION

[0070] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0071] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0072] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0073] Example 1, with reference to Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a method for protecting mobile phone information privacy based on big data analysis, comprising the following steps:

[0074] S1. Collect the latest privacy protection requirements from the application market and / or regulatory authorities, extract privacy protection clauses, and generate a standardized privacy protection rule dataset. The specific steps are as follows:

[0075] S11. Collect privacy protection requirements from the application market and / or regulatory authorities. The main data sources involved include the application market privacy policy and / or regulatory provisions.

[0076] App market privacy policy: Google Play Store, Apple App Store, etc.

[0077] Automatically obtain the latest privacy protection requirements from app markets and / or regulatory authorities through public API interfaces (such as the Google Play Developer API) and web crawlers; privacy protection requirements include privacy protection terms and policies.

[0078] For example, assuming there are N application markets and M privacy protection clauses, the time complexity of data collection through API calls is , the expression is: .

[0079] It should also be noted that for privacy data that cannot be obtained through the API, a customized crawler system (such as Scrapy) should be used to crawl text information of privacy protection regulations from specific regulatory websites.

[0080] S12. Based on the obtained privacy protection requirements, use NLP methods (such as regular expressions and the natural language processing toolkit SpaCy) to clean up noisy data (HTML tags, special characters, and irrelevant text) to ensure data quality.

[0081] For example, assuming the length of the original input text is T, the noise ratio is p, and the length of the cleaned text is expressed as: .

[0082] Among them, the cleaned and segmented structured text data contains the privacy regulations of various application markets and regulatory authorities and is stored in structured JSON or CSV format.

[0083] S13. Use a pre-trained legal domain BERT model (such as Legal-BERT) to perform named entity recognition on the cleaned private text and extract privacy protection clauses.

[0084] It should be noted that the BERT model is a pre-trained language model based on the Transformer architecture that can generate context-sensitive word embeddings for natural language processing tasks. BERT's main innovation is that it is bidirectional, meaning that it considers both the preceding and following words when considering the context of a word.

[0085] The core of the BERT model consists of multiple TransformerEncoder layers, and its basic structure is as follows:

[0086] Input layer: The input sequence is usually a word sequence with special tags. The input format is: [CLS] + sentence 1 + [SEP] + sentence 2 + [SEP]; where [CLS] is a special classification tag used to represent the entire sequence, and [SEP] is used to separate sentences.

[0087] Embedding layer, TokenEmbedding: maps each word into a fixed-dimensional vector. SegmentEmbedding: distinguishes different sentences in the input, used to distinguish sentence 1 from sentence 2 in sentence classification tasks. PositionEmbedding: Since the Transformer has no built-in order information, BERT uses position embedding to encode the position of words in the sentence.

[0088] TransformerEncoder layer, each Encoder layer consists of two parts: a multi-head self-attention mechanism and a feedforward neural network, where:

[0089] Multi-Head Self-Attention Mechanism: BERT uses a multi-head self-attention mechanism to allow each word in the context to "pay attention" to all other words before and after it, thereby encoding contextual information.

[0090] Feed-forward Neural Network (FFN): The output after self-attention is transformed nonlinearly through a two-layer feed-forward neural network.

[0091] Different versions of the BERT model contain different numbers of encoder layers. BERT-base: 12 encoder layers, a hidden layer size of 768, 12 attention heads, and a total of 110M parameters.

[0092] BERT-large: 24 encoder layers, hidden layer size of 1024, 16 attention heads, and a total of 340M parameters.

[0093] Output layer: In the pre-training task, BERT has two tasks, Masked Language Model (MLM): randomly mask some words in the input and require the model to predict these words.

[0094] Next Sentence Prediction (NSP): The model is required to determine whether two sentences are logically continuous sentences.

[0095] Furthermore, to adapt to legal tasks, the BERT model typically requires domain-adaptive pretraining on legal corpora. This is achieved through the following two steps: general BERT pretraining and legal domain-adaptive pretraining:

[0096] Specifically, universal BERT pre-training: Use the standard BERT pre-training process, including MLM and NSP tasks, but train on general general corpora (such as Wikipedia, BooksCorpus). This process helps the model learn universal language representations.

[0097] Adaptive pre-training in the legal domain and domain corpus collection: To adapt the BERT model to the characteristics of legal language, a large amount of legal text needs to be collected. Legal text includes but is not limited to: judgments, regulations, contract clauses, legal papers, privacy policies, etc.

[0098] Continue pre-training: Continue training the BERT model on legal domain corpus, using the same loss function as the original BERT (MLM and NSP tasks). The purpose of this step is to enable the model to better understand legal terminology, context, and regulations.

[0099] It should also be noted that the structure of the pre-trained legal BERT model is basically the same as the original BERT model, with the following differences:

[0100] Input structure: The input text mainly comes from legal documents such as privacy policies, regulations, and judgments. The input layer is labeled in the same way as BERT's standard input format (including [CLS] and [SEP] tags).

[0101] Embedding of legal domain corpus: Vocabulary: When pre-training in the legal domain, the model can use the standard BERT vocabulary or generate a new vocabulary based on the legal corpus. The new vocabulary will contain more legal terms and terminology.

[0102] Special legal terms and phrases are embedded into the model’s TokenEmbedding, allowing the model to better process and understand these terms.

[0103] TransformerEncoder layers: The number of Encoder layers is the same as the original BERT model (e.g., BERT-base or BERT-large), but these layers are further trained on legal domain corpora to better capture the contextual relationships in legal language.

[0104] Output layer: The output layer continues to perform MLM and NSP tasks during pre-training, but is performed on text in the legal field. The goal is to enable the model to have the ability to process legal language.

[0105] The preferred pre-trained legal domain BERT model, through domain-adaptive pre-training on legal corpora, can better understand and process legal documents related to privacy protection. While its structure is essentially the same as the standard BERT model, pre-training in the legal domain enhances the model's understanding of legal language and terminology, enabling it to more effectively extract key privacy protection information and generate a standardized dataset of privacy protection rules.

[0106] The legal domain BERT model is used to process and understand legal texts such as privacy protection clauses and policies. The pre-trained legal BERT model can achieve the following tasks:

[0107] Named Entity Recognition (NER): Extract key information from privacy policies, such as legal terms, personal information types, etc.

[0108] Semantic similarity calculation: Match legal terms expressed in different ways to ensure the consistency of privacy policies and regulations.

[0109] Rule mapping: Map the extracted entities to a standardized privacy protection clause framework to help generate a privacy protection rule dataset.

[0110] S14. According to privacy protection standards (such as GDPR provisions and CCPA requirements), map the extracted privacy protection terms to the privacy protection terms framework (such as GDPR and CCPA) to unify the format.

[0111] S15. Based on the unified format of the clause framework, use semantic similarity calculations (such as cosine similarity) to match regulatory clauses described in different languages ​​to ensure consistency of the clauses.

[0112] S16. Standardize regulatory provisions from different sources through rule mapping and hierarchical classification.

[0113] Specifically, based on semantic similarity, regulatory provisions from different sources are mapped into a unified privacy protection standard model. This standard model can be based on GDPR or CCPA.

[0114] The standardized mapping model uses weighted similarity scores to complete the term mapping.

[0115] Categorize clauses into different categories based on different dimensions of privacy protection (e.g., data collection, data processing, user consent, etc.). Use a hierarchical classification tree for automated classification.

[0116] Output: A standardized privacy protection clause dataset, where each clause is mapped to a specific standard and classified into the corresponding privacy protection dimension.

[0117] S17. Use rule engines and knowledge graphs to verify and check the consistency of standardized regulatory clauses to form a standardized privacy protection rule dataset.

[0118] S2. Based on the privacy-preserving rule dataset, distributed training and encrypted aggregation are used to generate global model parameters, including:

[0119] S21. Use a hierarchical federated learning architecture to group privacy-preserving rule datasets into different nodes and layers, where each layer represents a different data grouping or privacy-specific cluster. For example, the bottom layer could be a specific application category (e.g., financial applications, social media applications), the middle layer could be an industry (e.g., finance, healthcare), and the top layer could be a country or region.

[0120] S22. At each node of each layer, based on the respective data grouping, the model is trained using the local privacy rule dataset to obtain the model parameters of each layer.

[0121] S23. Each node calculates the loss function based on the local privacy rule dataset and updates the model parameters of each layer by optimizing the loss function.

[0122] Calculating the loss function The expression is:

[0123] ;

[0124] in, Indicates the The loss value of each node, represents the model parameters, Indicates the The number of data samples per node, is the index variable for summation, represents the loss function, Representation Model For input data The predicted value of express The first of the nodes The input features of the data samples, Indicates the The first of the nodes The target value of the samples, Represents the index of the node, The index variable representing the sum;

[0125] The local privacy rule dataset provides local training data for each node, including input features and target value ;

[0126] Among them, the local privacy rule dataset refers to the privacy protection rule subset generated by each node based on its local user data and relevant privacy protection requirements (such as privacy terms, laws and regulations, privacy policies, etc.), which contains data samples unique to the node. and the corresponding labels In the expression and In fact, it is the samples and target values ​​extracted from the local privacy rule dataset of the node. The use of this dataset ensures that the user's sensitive information will not be leaked during the model training process.

[0127] Specifically, the privacy protection rules dataset is a complete privacy protection rules data set generated by collecting privacy protection requirements, privacy terms and policies from application markets, regulatory authorities, etc. after cleaning, standardization, mapping and verification.

[0128] Local privacy rule dataset: In federated learning or distributed systems, a complete privacy-preserving rule dataset is distributed to each node. Each node only holds a subset of privacy-preserving rules relevant to its local data, called the "local privacy rule dataset." This dataset is used for training locally on the node, ensuring that data is not directly shared between nodes.

[0129] For example, suppose there are multiple nodes in a federated learning system, each of which holds the privacy data of different users: Global privacy rule dataset: contains the privacy protection terms, privacy policies, data usage rules, etc. of all users, and is aggregated from multiple data sources (such as laws, regulations, and privacy policies of different countries).

[0130] Local privacy rule dataset: Each node only uses rules related to its local user privacy data.

[0131] The specific "local privacy rule dataset" may include:

[0132] Privacy terms: Privacy terms related to the user's private data managed by the node. For example, the user's privacy protection terms for location data, address book, SMS, sensor data, etc.

[0133] Laws and regulations: Privacy protection laws and regulations related to specific regions, covering requirements for data collection, storage, processing, sharing, etc.

[0134] Privacy Policy: The privacy policy established by the application market, developer, or company specifies how the node handles user privacy data and requires compliance with specific privacy protection standards.

[0135] Sensitive data types: Which user data managed by this node is sensitive (such as GPS location, health data, financial data, etc.) and the protection rules for this data.

[0136] Data processing rules: How to handle user data according to privacy terms and regulations, including data encryption, storage, transmission and other requirements.

[0137] S24. Send the updated model parameters of each layer to the central server of that layer through encrypted communication, and use multi-party secure computing (MPC) to encrypt and aggregate the parameters within the layer and output the global model parameters, which are expressed as:

[0138] ;

[0139] in, Indicates in After the round of training, the global model parameters are updated. Express The parameters of each node are weighted averaged. Indicates the total number of nodes, Indicates the The node in The local model parameters obtained after rounds of training, Indicates the round of iteration.

[0140] It should be noted that, first of all, the local model parameters are the model parameter results obtained by each node through local training; the intra-layer parameters are composed of the local model parameters trained by multiple nodes in the same layer, which are sent to the central server of the layer through encrypted communication; the updated model parameters of each layer are the global model parameters obtained after these local model parameters are aggregated through multi-party secure calculation and encryption.

[0141] It should be noted that "multi-party secure computation" is a method used to ensure data privacy, allowing multiple participants to collaborate on computing tasks without disclosing their own data. In this context, multi-party secure computation can be used to achieve secure aggregation of model parameters. That is, without directly exchanging original data, all participants can jointly compute updated values ​​for a global model. Furthermore, multi-party secure computation (MPC) primarily focuses on protecting data privacy within a single computation, rather than directly involving multiple rounds of training. However, during the multi-round training process of federated learning, MPC can be applied multiple times to ensure data privacy and security within each iteration. Therefore, while MPC supports multi-round training in federated learning, it is not itself a multi-round training process.

[0142] It should be noted that the expression This describes a parameter aggregation method in federated learning. Federated learning is essentially an iterative process, where each participant continuously updates their model over multiple rounds until convergence conditions are reached. After each round of training, the global model parameters are updated using the above formula or other similar methods.

[0143] It should also be noted that servers should use secure multi-party computation (MPC) for parameter aggregation to ensure that no private data is leaked during the aggregation process. Furthermore, in a layered architecture, after lower-level aggregation is completed, the parameters of each layer are submitted to higher-level servers until the top-level server completes the final global model aggregation. After the top-level model is aggregated, the global model parameters are generated.

[0144] To ensure data privacy during training, group computing and key sharing are used within each layer (during training and aggregation of each layer) to protect privacy. The expression is:

[0145] ;

[0146] in, Indicates the The encryption result of each node, Indicates the total number of generated partial keys, is the index of the partial key, Indicates the The node A partial key.

[0147] It should be noted that in the aggregation process of each layer, hierarchical MPC is adopted, that is, MPC calculations are first performed inside the nodes of each layer to ensure that the data of this layer will not be leaked, and then the encrypted results are submitted to the upper-level server for further aggregation.

[0148] Preferably, the combination of group computing and hierarchical MPC can effectively reduce the computing pressure of each node and improve the scalability of the overall system. The MPC calculation at each level only needs to process the data of this level, reducing the complexity of cross-layer data transmission.

[0149] A dynamic optimization mechanism is introduced to adjust global model parameters to adapt to changes in different privacy scenarios.

[0150] By regularly checking the performance of the global model, the model parameters are dynamically adjusted for different privacy scenarios. The expression is:

[0151] ;

[0152] in, represents the learning rate, Represents the gradient of the global loss function;

[0153] Specifically, nodes at each level can use secure communication to provide feedback to the upper layer about difficulties encountered during training or changes in data distribution. The top-level server dynamically adjusts the training strategy of the global model based on this feedback.

[0154] Optimally, group computing and hierarchical MPC greatly reduce the computational burden of each layer, adapting to privacy-preserving training in large-scale distributed scenarios. MPC technology is used to perform secure computing between nodes at each level to ensure that data privacy is not leaked during the entire training process. Through a dynamic optimization mechanism, the model can adapt to changes in different privacy scenarios, ensuring the accuracy and flexibility of the global model.

[0155] S3. Use multi-party secure computing to encrypt and analyze the privacy data of mobile applications using global model parameters, including:

[0156] S31. Through global model parameters, coordinate each node to perform local training without sharing original data, and update the global model parameters through encrypted aggregation summary nodes.

[0157] S32. The updated global model parameters will be fed back to each node, and each node will collect local privacy data based on the updated global model parameters.

[0158] S33. Standardize local privacy data into a unified feature scale to ensure that data between different nodes can be effectively compared and aggregated, preparing for subsequent encryption and model training.

[0159] S34. Perform homomorphic encryption on the standardized local privacy data to generate an encrypted data set, ensuring that the data remains private during transmission and calculation, and calculations can be performed in an encrypted state.

[0160] The key of each node is sharded, dividing the key into several parts and distributing the sub-keys to multiple parties. The purpose is to increase the security of the data. Even if a sub-key is leaked, the complete key cannot be restored.

[0161] Among them, the original key can only be recovered when a sufficient number of key fragments are combined together, which ensures the security of the key.

[0162] S35. Each node performs local model training based on its own encrypted data set and calculates encrypted gradient data to prepare for subsequent global model updates.

[0163] S36. The encrypted gradient data is transmitted to the central server, and the encrypted gradient data of each node is encrypted and aggregated through multi-party secure computing (MPC) to obtain global encrypted gradient data. This can ensure that the central server can generate updates to the global model without leaking the specific gradient data of each node.

[0164] It should be noted that homomorphic encryption and secure multi-party computation (MPC) enable aggregation of encrypted gradient data without decrypting the gradients. MPC allows multiple participants to jointly compute the value of a function without exposing their own data. Combined with homomorphic encryption, gradients from each node can be securely aggregated in an encrypted state.

[0165] S37. By updating the gradient descent model parameters based on the dynamic changes of the time dimension based on the globally encrypted gradient data, gradient aggregation and global model updates are achieved under the fully encrypted state, preventing any single party (including the server) from accessing the plaintext data or model parameters, while ensuring that each node can use local data for effective model updates.

[0166] S38. Feedback the updated gradient descent model parameters to each node. Each node uses the subkey to decrypt the global gradient descent model parameters, ensuring that each node obtains the latest global model parameters and continues local training.

[0167] It should be noted that the purpose of this process is to ensure that the global model parameters remain encrypted during transmission and aggregation, and these parameters can only be obtained after each node decrypts them using the subkey. This mechanism ensures data privacy and security, preventing the server or other third parties from snooping on the model parameters during transmission.

[0168] The decrypted global gradient descent model parameters are combined with the encrypted gradient data of each node to generate encrypted analysis results. These analysis results include model performance evaluation, contribution analysis of each node, and a preliminary assessment of privacy leakage risks. While ensuring the accuracy of the model and the privacy of the data, this analysis result will be used for subsequent big data analysis.

[0169] It should be noted that the encrypted gradient data is the local encrypted gradient from each node; the global encrypted gradient data is the result obtained by aggregating the encrypted gradient data of all nodes.

[0170] The connection between the two is that the global encrypted gradient data is the gradient information from a global perspective obtained by encrypting and aggregating the encrypted gradient data of multiple nodes, which is used to update the global model.

[0171] S4. After obtaining the encryption analysis results, combine them with big data analysis to generate a dynamic privacy protection rule file. The specific steps are as follows:

[0172] S41. Input the generated encryption analysis results and global model parameters into the big data analysis engine to evaluate the performance of the global encrypted gradient data, including the model's convergence, node contribution, and training efficiency, as follows:

[0173] Model convergence, which is used to evaluate the convergence speed of the model during training and determine whether there are signs of overfitting or underfitting;

[0174] Node contribution, used to analyze the contribution of each node to the model (based on gradient changes) and determine whether there are abnormal nodes or data deviations;

[0175] Training efficiency, used to evaluate the training efficiency and communication latency of nodes and identify network bottlenecks or computing bottlenecks.

[0176] S42. After the performance evaluation, the big data analysis engine conducts a privacy risk analysis based on the encryption analysis results. Specifically, it analyzes the privacy leakage risk, including whether the private data of a certain node can be inferred through the global model; confirms whether the currently used homomorphic encryption algorithm is strong enough and whether the encryption key length or algorithm needs to be adjusted.

[0177] S43. The big data analytics engine generates privacy protection recommendations based on the performance evaluation results and privacy risk analysis results using rule-based reasoning (RBR) and machine learning models (e.g., supervised learning models). These recommendations include:

[0178] Encryption algorithm adjustment: whether it is necessary to increase the encryption strength or change the encryption algorithm in the next round of training.

[0179] Node-level privacy policy: Generates a personalized privacy protection policy for each node to control potential privacy leakage risks.

[0180] S44. Based on the privacy risk analysis results and privacy protection recommendations, a dynamic privacy protection rule file is generated through automated reasoning of the decision tree. The specific process is as follows:

[0181] Train a decision tree model to learn the best privacy-preserving strategy under different privacy risk and performance conditions.

[0182] Input big data analysis results and let the decision tree generate the most appropriate privacy protection strategy.

[0183] Convert the generated policy into a standardized dynamic privacy protection rule file (such as JSON or XML).

[0184] Save and distribute the rule files for use by each training node.

[0185] Among them, the big data analysis results specifically include privacy risk assessment results, privacy compliance analysis reports, system resource consumption and performance evaluation, application behavior detection reports, user privacy preference and behavior analysis results, and feedback and improvement suggestions on privacy protection models.

[0186] Specifically, privacy protection rules documents typically refer to a set of policies and technical measures used to protect data privacy, particularly in areas such as distributed systems, federated learning, and data processing. The goal of these rules is to prevent unauthorized access or leakage of sensitive data while maximizing system performance while ensuring privacy.

[0187] Specifically, it includes encryption rules: encryption algorithm, key length, encrypted data transmission, etc.; differential privacy rules: enabling differential privacy and parameter setting (such as ε and δ); data processing rules: data sampling, data sharding, anonymization, etc.; security aggregation rules: using secure multi-party computing and security aggregation technology to protect data privacy; access control and permission management: role access control, zero trust architecture, principle of least privilege, etc.; dynamic privacy protection rules: rule update frequency, adaptive privacy protection strategy, etc.; log audit and monitoring rules: privacy event monitoring and audit log management.

[0188] It should also be noted that these rules can be flexibly combined and dynamically adjusted according to different privacy requirements and data scenarios to ensure that system performance is maximized while protecting privacy.

[0189] S5. For the dynamic privacy protection rule file, the ASM framework is used to parse the bytecode of the mobile application, automatically modify sensitive API call points, and insert privacy monitoring logic. The specific steps are as follows:

[0190] S51. Decompile the APK using apktool to obtain the .dex file. APK stands for Android Package, which is translated into Android Application Package in Chinese.

[0191] S52. Use dex2jar to convert the .dex file into .class bytecode.

[0192] S53. Use the ASM framework to parse the decompiled .class bytecode and read each .class bytecode through ClassReader to generate the class structure tree of the file. ClassReader is the core class in the ASM framework for reading .class files. It is responsible for parsing Java bytecode and passing various parts of the class file (such as fields and methods) to ClassVisitor for further processing or modification. At the same time, as the starting point of the bytecode modification tool chain, ClassReader is used in conjunction with classes such as ClassVisitor and MethodVisitor to implement in-depth operations and modifications on Java class files.

[0193] S54. All method calls are captured by overriding the visitMethod method, all Java methods are captured in the class structure tree, and processed to generate a bytecode interceptor for each Java method.

[0194] The visitMethod method is a key method in the ASM framework, used to capture and process each method definition in a class. Developers can use it to create a MethodVisitor for each method to modify the bytecode instructions within the method. This is the key entry point for modifying method behavior during the bytecode modification process.

[0195] S55. Combine the dynamic privacy protection rule file and the bytecode interceptor to automatically identify sensitive API call points in the .class bytecode. The rule file defines a list of sensitive APIs that need to be monitored (such as location, camera, and contact access). During the bytecode parsing process, each method call is compared with this list to identify sensitive APIs that need to be modified.

[0196] S56. At the identified sensitive API call points, use ASM's MethodVisitor to insert bytecode for calling the privacy monitoring method (such as recording call information, user authorization judgment, etc.) before the Java method call instruction, and insert result processing logic after the Java method call to ensure that the use of sensitive APIs is monitored and restricted in real time; MethodVisitor is a class name in the ASM framework that is dedicated to bytecode operations.

[0197] It should be noted that the specific content of monitoring logic can include recording the time of API calls, passed parameters, call results, etc., or directly blocking certain calls according to the requirements of the rule file. In the ASM MethodVisitor, monitoring code is inserted to enable the tracking or restriction of sensitive API calls.

[0198] S6. Repackage the modified sensitive API call points into an APK file and perform privacy monitoring verification on the application.

[0199] S61. Use the d8 tool to repackage the modified .class file into a .dex file, replace the original .dex file, and generate a new .dex file.

[0200] S62. Replace the new .dex file into the decompiled file structure, and use apktool to repackage and generate a new APK file.

[0201] S63. Use the developer key to sign the new APK file to ensure that it can be installed and run on the Android device and installed on the smart terminal device.

[0202] It should be noted that when signing an APK file, you need to ensure that the correct key and alias are used. If the key is lost or the wrong key is used, the APK will not be installed correctly on the device. At the same time, if you want to publish it to Google Play, you also need to ensure that the signature of the APK is consistent with the previously released version.

[0203] S64. Use automated testing tools (such as Espresso or UIAutomator) to verify whether the call points of sensitive APIs trigger the inserted privacy monitoring logic. If the inserted privacy monitoring logic is triggered, it means that the sensitive API call points are captured by the monitoring logic, relevant log records are generated, and privacy protection measures are executed. If the inserted privacy monitoring logic is not triggered, it means that the sensitive API call points are not captured, and relevant information about the monitoring logic is missing in the log. Check the bytecode, and modify and verify the test environment until the inserted privacy monitoring logic is successfully triggered.

[0204] It should be noted that the privacy monitoring logic includes pre-logic and post-logic, as follows:

[0205] Pre-processing logic: Whether the inserted privacy monitoring method is successfully executed before calling the sensitive API call point.

[0206] Post-processing logic: Whether the inserted result processing logic is successfully executed after the call point of the sensitive API is called.

[0207] This embodiment also provides a mobile phone information privacy protection system based on big data analysis, including: an information collection module, a global model parameter generation module, an encryption analysis module, a dynamic privacy protection rule file generation module, a bytecode modification module and a verification module; the information collection module is used to collect the latest privacy protection requirements from the application market and regulatory authorities, extract key privacy protection information, and generate a standardized privacy protection rule data set; the global model parameter generation module is used to generate global model parameters based on the privacy protection rule data set using distributed training and encryption aggregation; the encryption analysis module is used to perform encryption analysis on the privacy data of mobile phone applications using multi-party secure computing on the global model parameters; the dynamic privacy protection rule file generation module is used to generate a dynamic privacy protection rule file in combination with big data analysis after obtaining the encryption analysis results; the bytecode modification module is used to parse the bytecode of the mobile phone application through the ASM framework for the dynamic privacy protection rule file, automatically modify sensitive API calls and insert privacy monitoring logic; the verification module is used to repackage the modified bytecode into an APK file and perform privacy monitoring verification on the application.

[0208] This embodiment also provides a computer device, which is suitable for the mobile phone information privacy protection method based on big data analysis, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the mobile phone information privacy protection method based on big data analysis proposed in the above embodiment.

[0209] The computer device may be a terminal, comprising a processor, memory, a communication interface, a display, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system and computer programs. The internal memory provides an environment for the operating system and computer programs stored in the non-volatile storage media. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication. Wireless communication may be achieved via Wi-Fi, a carrier network, NFC (near-field communication), or other technologies. The display of the computer device may be a liquid crystal display or an electronic ink display. The input device may be a touchscreen overlay on the display, buttons, a trackball, or a touchpad on the computer device housing, or an external keyboard, touchpad, or mouse.

[0210] This embodiment also provides a storage medium having a computer program stored thereon. When the program is executed by a processor, the method for protecting mobile phone information privacy based on big data analysis proposed in the above embodiment is implemented. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0211] In summary, by combining technologies such as big data analysis, federated learning, and multi-party secure computing, the present invention can realize dynamic and real-time privacy protection rule generation and updating, overcoming the problems of lag and static nature of privacy protection rules in the existing technology; secondly, it can keep up with the latest privacy protection regulations and standards in a timely manner, automatically modify sensitive API call points in applications, and improve the flexibility of privacy protection; in addition, the present invention adopts encryption analysis and distributed training to ensure the secure sharing and processing of privacy data with the participation of multiple parties, effectively enhancing the protection of mobile phone information privacy, and is suitable for complex and changeable application scenarios.

[0212] Example 2, referring to Table 1, is the second embodiment of the present invention. In order to further verify the technical solution of the present invention, experimental simulation data of the mobile phone information privacy protection method based on big data analysis is provided.

[0213] The experiment selected five applications with high privacy risks, including social media, instant messaging, financial payment, health data management, and online shopping. Without any privacy protection measures, these applications commonly suffer from excessive collection of sensitive information and unauthorized API calls. The experiment compared existing privacy protection schemes with the proposed solution to evaluate their respective privacy protection effectiveness.

[0214] The experiment is divided into two stages: data collection and preprocessing, and comparison of privacy protection schemes.

[0215] Data Collection and Preprocessing: Using web crawlers and public APIs, we retrieve the latest privacy protection terms and related regulatory information from app markets and regulatory authorities. We use natural language processing (NLP) to clean up noisy data in privacy protection terms, and employ a pre-trained BERT model for named entity recognition to extract key information from the privacy protection terms. This step provides a foundation for the subsequent generation of privacy protection rules.

[0216] Among them, "named entities" refer to key information or terms with specific legal significance in privacy texts. These entities are usually concepts or nouns involved in privacy policies and legal clauses, and have attributes related to law or privacy protection. Specific named entities (NamedEntities) can include the following:

[0217] Types of personal information: such as "name," "ID number," "email address," "telephone number," "geolocation data," etc. Privacy protection clauses usually clearly list what types of personal information will be collected, processed, or shared.

[0218] Name of law or regulation: The name of the law, regulation, or standard related to privacy protection, such as the General Data Protection Regulation (GDPR), the California Consumer Privacy Act (CCPA), etc.

[0219] Organization Name: The name of the company, regulator, or third-party organization involved in privacy protection.

[0220] Data processing activities: specific operations for processing personal data described in the terms, such as "collection", "storage", "sharing", "deletion", "encryption", etc.

[0221] Time and date: refers to the time limit or validity period specified in the privacy protection terms, such as "data retention period", "time limit for data deletion" or "policy effective date".

[0222] Location: This refers to the geographical location where data is stored or processed.

[0223] Privacy rights: the rights that users enjoy in the privacy protection terms, such as "right to access", "right to deletion", "right to data portability", "right to object", etc.

[0224] For example, suppose there is a privacy protection clause as follows:

[0225] The Company collects the user's name, email address, and phone number. The user has the right to request that the Company delete their personal data, and the data will be stored only within the EU.

[0226] In this text, named entities can be: name (personal information type), email address (personal information type), phone number (personal information type), GDPR (name of the law), and EU location (geographic location).

[0227] These key information (named entities) are a very important part of the privacy policy. They can help understand the specific content and requirements of the privacy protection clauses, and then extract the privacy protection clauses to provide a basis for subsequent rule-making and privacy monitoring.

[0228] Comparison of Privacy Protection Solutions: Existing Technology Solutions: Privacy protection methods based on static cryptographic analysis. Existing technology solutions typically perform cryptographic analysis on the application's private data and define and test fixed privacy rules at the application level. This solution is characterized by centralized encryption processing using a single server, lacking the ability to dynamically adjust privacy protection rules, and lacking distributed data processing capabilities. When protecting privacy, calls to sensitive APIs rely solely on pre-set static rules, which cannot adapt to the dynamic changes in privacy risks in real applications.

[0229] The solution of the present invention: A privacy protection solution based on big data analysis and federated learning. This solution first distributes the privacy protection rule dataset to multiple nodes through a distributed federated learning architecture, and performs local training on each node. During the training process, multi-party secure computing technology is used to encrypt, transmit and aggregate the model parameters between nodes to ensure that private data is not leaked during transmission. Subsequently, combined with homomorphic encryption methods, dynamic encryption analysis is performed on the privacy data of mobile phone applications, and the generated privacy protection rule file can be dynamically adjusted according to real-time privacy risks. Finally, the application bytecode is automatically modified through the ASM bytecode parsing framework, privacy monitoring logic is inserted, and the new APK file is repackaged.

[0230] Cryptographic Analysis and Rule Generation: Existing solutions use static cryptographic analysis methods, where privacy protection rules rely on pre-set static models and cannot dynamically generate new protection rules. The present invention, however, uses a big data analysis engine to assess privacy risks based on cryptographic analysis results and generates new privacy protection rules based on dynamic privacy risks.

[0231] Bytecode Modification and Verification: Both solutions modify the application's bytecode and insert privacy monitoring logic. Existing solutions manually mark sensitive APIs and insert fixed monitoring logic, while the present invention combines dynamic privacy protection rule files for automated bytecode modification and sensitive API identification.

[0232] Furthermore, the experiment compared the privacy protection effects of unprotected, existing technical solutions and the solution of the present invention. The key indicators of the experiment include: the reduction rate of API sensitive calls, privacy leakage risk score, application performance impact and privacy monitoring trigger rate.

[0233] The details are shown in Table 1 below:

[0234] Table 1 Experimental data comparison table

[0235]

[0236] The experimental data comparison results are shown in the table above. The existing technical solutions and the solution of the present invention show significant differences in multiple privacy protection indicators, as follows:

[0237] Reduction in the number of sensitive API calls: In unprotected applications, sensitive APIs are called as many as 120 times. Existing technical solutions can reduce the number of sensitive API calls to 80 times through static encryption analysis and fixed rule detection, a reduction of about 33%. However, since existing technical solutions cannot dynamically adjust privacy protection rules, calls to sensitive APIs are still relatively frequent. The solution of the present invention generates dynamic privacy protection rules through big data analysis and automatically adjusts the API call strategy, further reducing the number of sensitive API calls to 30 times, a reduction of 62.5% compared to existing technologies. This shows that the solution of the present invention has significant advantages in real-time monitoring and dynamic adjustment of privacy risks.

[0238] Privacy Leakage Risk Score: The privacy leakage risk score is an important indicator for measuring the privacy protection capabilities of an application. The privacy leakage risk score of an unprotected application is 85 points, indicating that it faces a high risk of privacy leakage. The existing technical solution reduces the risk score to 50 points through static encryption analysis and detection. Although the risk is reduced, it cannot cope with dynamically changing privacy risks due to the static nature of the rules. The solution of the present invention realizes distributed encryption analysis of privacy data through federated learning and multi-party secure computing technology, and combines big data analysis to generate dynamic privacy protection rules, further reducing the risk score to 10 points. Compared with the existing technology, the solution of the present invention significantly improves the accuracy and flexibility of privacy protection.

[0239] Application Performance Impact: Existing privacy protection solutions have a certain impact on actual application performance, primarily due to a decrease in application response speed due to the insertion of cryptographic analysis and privacy monitoring logic. While existing solutions have a 10% performance impact, the proposed solution reduces this to 5% through optimized cryptographic calculations and model update mechanisms. While protecting privacy, the proposed solution minimizes the negative impact on application performance, ensuring that the user experience is not significantly impacted.

[0240] Privacy monitoring trigger rate: The privacy monitoring trigger rate refers to the frequency with which the privacy monitoring logic successfully captures and responds to calls to sensitive APIs by applications. The existing technology solution has a privacy monitoring trigger rate of 60%, which can capture calls to sensitive APIs in most cases. However, due to the static nature of its rules, there is still a risk that some sensitive API calls may not be monitored. The solution of the present invention, through dynamically generated privacy protection rules, can capture calls to sensitive APIs in the vast majority of cases, with a monitoring trigger rate of up to 95%, indicating that its comprehensiveness and real-time performance of privacy protection have been greatly improved.

[0241] In summary, the present invention's mobile phone information privacy protection method based on big data analysis outperforms existing solutions in many aspects. Compared to traditional static encryption analysis methods, the present invention's solution, through federated learning and big data analysis, achieves dynamic generation and adjustment of privacy protection rules. This can more effectively reduce the number of sensitive API calls and mitigate the risk of privacy leaks, ensuring comprehensive privacy protection for applications without sacrificing user experience.

[0242] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A mobile phone information privacy protection method based on big data analysis, characterized in that: include: Collect the latest privacy protection requirements from the application market and / or regulatory authorities, extract privacy protection clauses, and generate a standardized privacy protection rule dataset; Based on the privacy-preserving rule dataset, distributed training and encrypted aggregation are used to generate global model parameters. The specific steps are as follows: Using a hierarchical federated learning architecture, privacy-preserving rule datasets are grouped into different nodes and layers. At each node in each layer, model training is performed using the local privacy rule dataset based on the respective data grouping to obtain the model parameters for each layer. Each node calculates the loss function based on the local privacy rule dataset and updates the model parameters for each layer by optimizing the loss function. The updated model parameters of each layer are sent to the central server of that layer through encrypted communication, and multi-party secure computing is used to encrypt and aggregate the parameters within the layer to output the global model parameters. During the aggregation process of each layer, hierarchical MPC encryption calculations are performed within the nodes of each layer, and the encrypted results are submitted to the upper-layer server for further aggregation. For global model parameters, multi-party secure computing is used to perform encryption analysis on the privacy data of mobile applications. After obtaining the encryption analysis results, a dynamic privacy protection rule file is generated in combination with big data analysis. The specific steps are as follows: The generated encryption analysis results and global model parameters are input into the big data analysis engine to evaluate the performance of the global encrypted gradient data; the big data analysis engine performs privacy risk analysis based on the encryption analysis results; The big data analysis engine generates privacy protection recommendations based on performance evaluation results and privacy risk analysis results using rule-based reasoning and machine learning models; Generate dynamic privacy protection rule files through decision trees based on privacy risk analysis results and privacy protection recommendations; For dynamic privacy protection rule files, the ASM framework is used to parse the bytecode of mobile applications, automatically modify sensitive API call points, and insert privacy monitoring logic. The specific steps are as follows: Use apktool to decompile the APK to obtain the .dex file; use dex2jar to convert the .dex file into .class bytecode; use the ASM framework to parse the decompiled .class bytecode, and read the .class bytecode through ClassReader to generate a class structure tree for the file; by rewriting the visitMethod method, all Java methods in the class structure tree are captured and processed to generate a bytecode interceptor for each Java method; combine the dynamic privacy protection rule file and the bytecode interceptor to automatically identify sensitive API call points in the .class bytecode; at the identified sensitive API call points, use ASM's MethodVisitor to insert the bytecode of the privacy monitoring method before the Java method call, and insert the result processing logic after the Java method call; repackage the modified sensitive API call points into an APK file, and perform privacy monitoring verification on the application.

2. The method for protecting mobile phone information privacy based on big data analysis according to claim 1, characterized in that: The specific steps for collecting the latest privacy protection requirements from the application market and / or regulatory authorities, extracting privacy protection clauses, and generating a standardized privacy protection rule dataset are as follows: Automatically obtain the latest privacy protection requirements from app markets and / or regulatory authorities through public APIs and web crawlers. Privacy protection requirements include privacy protection terms and policies. Based on the privacy protection requirements obtained, we use NLP methods to clean up the noise data in the private text. We use the pre-trained legal domain BERT model to perform named entity recognition on the cleaned private text and extract the privacy protection clauses. According to the privacy protection standards, the extracted privacy protection clauses are mapped to the clause framework for format unification; based on the unified clause framework, semantic similarity is used to match regulatory clauses described in different languages; through rule mapping and hierarchical classification, regulatory clauses from different sources are standardized; the standardized regulatory clauses are verified and consistency checked using rule engines and knowledge graphs to form a standardized privacy protection rule dataset.

3. The method for protecting mobile phone information privacy based on big data analysis according to claim 2, characterized in that: The global model parameters are expressed as: Among them, θ (t+1) represents the global model parameters obtained after the t+1 round of training, Indicates the weighted average of the parameters of N nodes, where N represents the total number of nodes. represents the local model parameters of the i-th node after the t-th round of training, and t represents the number of iterations.

4. The method for protecting mobile phone information privacy based on big data analysis according to claim 3, characterized in that: The global model parameters are encrypted and analyzed using multi-party secure computing on the private data of mobile phone applications. The specific steps are as follows: Through global model parameters, each node is coordinated to perform local training without sharing original data. The global model parameters are updated by summarizing the nodes through encrypted aggregation. The updated global model parameters are fed back to each node, and each node collects local private data based on the updated global model parameters. The local private data is normalized to a unified feature scale. The standardized local private data is homomorphically encrypted to generate an encrypted dataset. Each node performs local model training based on its own encrypted dataset and calculates encrypted gradient data. The encrypted gradient data is transmitted to the central server, and the encrypted gradient data of each node is encrypted and aggregated through multi-party secure computing to obtain the global encrypted gradient data. The gradient descent model parameters are updated based on the dynamic changes in the time dimension based on the global encrypted gradient data. The updated gradient descent model parameters are fed back to each node, and each node uses the subkey to decrypt the global gradient descent model parameters; the decrypted global gradient descent model parameters are combined with the encrypted gradient data of each node to generate encrypted analysis results.

5. The method for protecting mobile phone information privacy based on big data analysis according to claim 4, characterized in that: The modified sensitive API call points are repackaged into an APK file, and the application is subjected to privacy monitoring verification. The specific steps are as follows: Use the d8 tool to repackage the modified .class bytecode into a .dex file, replace the original .dex file, and generate a new .dex file; Replace the new .dex file into the decompiled file structure and use apktool to repackage and generate a new APK file; Sign the new APK file with the developer key and install it on the smart terminal device. Use automated testing tools to verify whether the call points of sensitive APIs trigger the inserted privacy monitoring logic. If the inserted privacy monitoring logic is triggered, it means that the sensitive API call point is captured by the monitoring logic, relevant log records are generated, and privacy protection measures are executed; If the inserted privacy monitoring logic is not triggered, it means that the sensitive API call point is not captured and the log lacks relevant information about the monitoring logic. Check the bytecode and modify and verify the test environment until the inserted privacy monitoring logic is successfully triggered.

6. A mobile phone information privacy protection system based on big data analysis, based on the mobile phone information privacy protection method based on big data analysis according to any one of claims 1 to 5, characterized in that: include: Information collection module, global model parameter generation module, encryption analysis module, dynamic privacy protection rule file generation module, bytecode modification module and verification module; The information collection module is used to collect the latest privacy protection requirements from the application market and / or regulatory authorities, extract privacy protection clauses, and generate a standardized privacy protection rule dataset; The global model parameter generation module generates global model parameters based on the privacy protection rule dataset using distributed training and encrypted aggregation; The encryption analysis module is used to perform encryption analysis on the privacy data of mobile phone applications using multi-party secure computing on global model parameters; The dynamic privacy protection rule file generation module is used to generate a dynamic privacy protection rule file in combination with big data analysis after obtaining the encryption analysis results; The bytecode modification module is used to parse the bytecode of the mobile application through the ASM framework for the dynamic privacy protection rule file, automatically modify sensitive API call points, and insert privacy monitoring logic; The verification module is used to repackage the modified sensitive API call points into an APK file and perform privacy monitoring verification on the application.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the mobile phone information privacy protection method based on big data analysis according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the mobile phone information privacy protection method based on big data analysis according to any one of claims 1 to 5 are implemented.

Images