408 results about "Secure computing" patented technology

A method for using a local large language model (LLM) within a user's secure computing environment is disclosed. The LLM operates behind a firewall to prevent transmission of sensitive data, and utilizes an encrypted vector database and artificial intelligence techniques for content retrieval, response generation, and task anticipation. This system can be used on mobile, wearable, vehicle, or IoT devices and offers various services such as health monitoring, financial advice, automated communications handling, and personalized daily activity optimization. It also has the ability to detect fraud, fine-tune responses using augmented user data, assist in negotiations, identify personal interests, and provide health recommendations based on dietary and physical activity data.

A method for using a local large language model (LLM) within a user's secure computing environment is disclosed. The LLM operates behind a firewall to prevent transmission of sensitive data, and utilizes an encrypted vector database and artificial intelligence techniques for content retrieval, response generation, and task anticipation. This system can be used on mobile, wearable, vehicle, or IoT devices and offers various services such as health monitoring, financial advice, automated communications handling, and personalized daily activity optimization. It also has the ability to detect fraud, fine-tune responses using augmented user data, assist in negotiations, identify personal interests, and provide health recommendations based on dietary and physical activity data.

The present invention relates to the field of privacy computation. Disclosed are a secure multi-party computation method and system based on a decision tree and privacy protection. In a data processing stage, the method uses a gradient-based one-sided sampling algorithm, so as to exclude most small-gradient samples, thus ensuring balance in accuracy while reducing the data volume; then, the method uses a histogram algorithm to construct a decision tree, thus reducing the memory consumption and increasing the computational speed; and in addition, the method also uses a differential privacy technology to perform encryption and perturbation processing on parameters of local models, so as to ensure that individual privacy information is not leaked. The secure multi-party computation method based on a decision tree and privacy protection of the prevent invention can implement prediction tasks such as classification efficiently and reliably while protecting privacy.

The invention discloses a customer privacy protection method based on homomorphic encryption and data desensitization, and particularly relates to the technical field of data privacy protection. Original customer data are collected, data cleaning, standardization and sensitive information identification and classification are carried out, the identified customer sensitive information is dynamically calculated, and differential privacy noise parameters are applied, so that the customer privacy protection is realized. The method comprises the following steps: generating dynamic desensitization data, encrypting key numerical sensitive information in the generated dynamic desensitization data, generating ciphertext data, and constructing a security calculation and analysis platform which comprises a ciphertext calculation engine and a security query interface and is used for executing ciphertext addition and multiplication operations on the generated ciphertext data to form an encryption analysis result. Authorization decryption and result delivery are carried out on the encrypted analysis result, and the privacy protection effect and the data use condition of the whole process are recorded in an audit log, so that traceable privacy protection closed-loop management is realized.

According to the electric bicycle data collaborative sharing method based on multi-party security computing, the collaborative computing system is constructed, the collaborative control nodes in the collaborative computing system are independent of the business departments, and the collaborative computing system allocates at least one computing execution node to each business department. The calculation execution nodes are in communication connection with a database of a business department, and each calculation execution node is in communication connection with the coordination control node; the method comprises the following steps: splitting a calculation task in a collaborative governance service related to cross-department data sharing based on service logic, and obtaining a single-department calculation sub-task and a cross-department calculation sub-task after splitting; each calculation execution node executes a calculation task which only relates to the data of the business department, and only submits a calculation result to the coordination control node; all calculation tasks related to cross-department data are completed at the coordination control node; and then the coordination control node feeds back the data requested by the business department to the requesting department.

The invention relates to the technical field of confidential computing, and discloses a data credibility-oriented vehicle-mounted integrated security computing system and credibility construction method, which comprises the following steps of: establishing a static trust chain by using a hardware trust root, shielding external interruption in a credible execution environment, and controlling a performance monitoring unit; synchronously collecting real-time hardware micro-architecture events of the key business algorithm to generate a runtime feature vector; according to the method, the instruction stream during operation is anchored by utilizing the physical characteristics of the micro-architecture, the hijacking attack of the control stream is accurately identified in a ciphertext environment, the hijacking attack of the control stream is accurately identified, the hijacking attack of the control stream is accurately identified, the hijacking attack is accurately identified, and the hijacking attack of the control stream is accurately identified. Strong coupling verification of a calculation result and an execution behavior is realized, and logic safety of a vehicle-mounted platform is ensured.

The invention relates to the technical field of security computing, and discloses a privacy statistical method and system based on multi-party security computing and trusted execution environment collaboration.The method comprises the steps that threat intelligence statistical values collected by all security mechanisms are fragmented, and secret fragmentation values are obtained; calculating an enclave local certification structure according to the enclave environment safety parameters of the statistical nodes, and performing signature verification based on the enclave local certification structure to obtain a verification report; generating a session key based on the verification report, and performing encrypted transmission on the secret fragment value based on the session key to obtain an encrypted secret fragment; and reconstructing the encrypted secret fragment to obtain the threat intelligence statistical value, and carrying out multi-dimensional statistics on the threat intelligence statistical value to obtain a threat intelligence statistical result. According to the method and the system, multiple security assurance of threat intelligence privacy statistics is realized through a secret fragment and security enclave remote certification cooperation mechanism.

The invention relates to the technical field of computers, discloses an astronomical sensitive data security processing method, device and system based on privacy calculation, and a storage medium, and aims to solve the problems that in astronomical data cross-mechanism joint analysis, original data is easy to leak, the cooperation efficiency is low, and a traditional desensitization or encryption method is difficult to consider security and availability at the same time. The method specifically comprises the following steps: each participant deploys a private computing agent node locally, and original data is not out of a domain; the task coordination center issues an analysis task; the proxy node extracts and preprocesses local data, and loads a corresponding secure multi-party computing protocol template; according to the method, share segmentation is carried out on multi-modal data such as images, spectrums and star catalogues by adopting addition homomorphic secret sharing, and distribution is carried out through a national secret SM4 encryption channel; and multiple parties cooperatively execute task-oriented security calculation in an encrypted state, and the result is aggregated and returned with the minimum information amount. The method has the effect of realizing high-precision safe collaborative analysis which is available and invisible.

The present disclosure relates to techniques for automated and adaptive cloud security management. Embodiments provide for, at an electronic device configured to interface with a cloud computing environment, initiating one or more transactions in the cloud computing environment using a first identifier to cause a first service of the cloud computing environment to generate a first set of data including the first identifier and a second identifier, and a second service of the cloud computing environment to generate a second set of data including a third identifier and a fourth identifier. Embodiments also provide for automatically determining whether the first identifier corresponds to the third identifier, and, in accordance with a determination that the first identifier corresponds to the third identifier, associating the second identifier and the fourth identifier to generate a linkage between the first and second services.

The invention discloses a data privacy protection method based on multi-party security computing and a block chain, and the method comprises the following steps: 1, creating a multi-party security computing task request, and distributing the multi-party security computing task request to each participant node; 2, performing Kronecker perturbation coding on local original data, and performing Hash processing through an SHA-256 Hash algorithm to generate a perturbation Hash value; 3, recording access behaviors, and generating an access behavior track sequence; step 4, calculating a Soft-DTW distance between the access behavior track sequence and the historical access track sequence; 5, constructing an adjacent matrix and a Laplacian matrix, and carrying out eigenvalue decomposition; step 6, calculating the Euclidean distance between the access embedding vector and the legal access embedding vector; and 7, generating a result abstract and writing the result abstract into a task recording module. According to the method, the Kronecker perturbation coding and the Hash algorithm are combined, so that the data privacy protection, the calculation transparency and the compliance verification capability are improved.

Processing a payment transaction from a payer (operating a payer computing system) to a payee (operating a merchant computing system) by a secure computing system. The secure computing system outputs a financial account registration request form to the payer computing system (e.g., within a window or frame that is displayed within an ecommerce webpage provided by the merchant computing system) for the payer to provide sensitive financial account information, securely stores the sensitive financial account information, maintains compliance with an information security standard (e.g., a Payment Card Industry Data Security Standard), and provides a non-sensitive electronic data token representing the sensitive financial account information to the merchant computing system. The merchant computing system can then process the payment transaction using the sensitive financial account information represented by the non-sensitive electronic data token without actually receiving—and, therefore, having to secure—the underlying sensitive financial account information.

The invention discloses a cloud edge collaborative information interaction processing device, method and system with an endogenous security architecture. The equipment comprises a main processor, a hardware security chip, a programmable logic unit, a communication unit and an equipment management unit. A trusted execution environment is constructed in the hardware security chip and is in isolated communication with a common execution environment of the main processor through a security bus, a security computing engine, a remote attestation module and a trusted key warehouse are arranged in the trusted execution environment, and the programmable logic unit is directly controlled by the trusted execution environment to realize dynamic hardware acceleration. The communication unit is provided with independent interfaces which are connected with the two execution environments respectively, unification of hardware-level security isolation and efficient cooperative computing is achieved, and the problems of privacy disclosure and untrusted process in cloud edge collaboration are solved.

The invention relates to the technical field of multi-party security computing, and discloses a high-performance reliable multi-party security computing technology test method and device and a storage medium, and the method comprises the steps: deploying a to-be-tested multi-party security computing platform and a corresponding preset test data set in a preset test system simulating multi-party participation; simulating multi-party calculation to obtain a ciphertext calculation result, and comparing an error between the ciphertext calculation result and the plaintext calculation result to obtain a first reliability confirmation result; the ciphertext calculation is repeatedly executed for multiple times, and time consumed by each time of calculation is obtained; comparing each time of time consumption with a preset time threshold to obtain a second reliability confirmation result; comparing the performance difference between the ciphertext training model and the plaintext training model to obtain a third reliability confirmation result; and when the three reliability confirmation results all meet the corresponding reliability judgment standards, confirming that the to-be-tested multi-party security computing platform is reliable. Therefore, the stability and credibility of the MPC platform in the actual service can be evaluated more comprehensively and accurately.

The embodiment of the invention discloses a safety calculation method and device for robot cluster collaboration and a medium, and relates to the technical field of safety calculation, and the method comprises the steps: carrying out the participant authentication of a robot cluster and a production enterprise node in advance, and carrying out the dynamic identity verification of each robot after the participant authentication is passed, the operation feature data of each target robot passing verification are extracted and encrypted, and encrypted feature vectors are determined; splitting the encrypted feature vector into a plurality of data fragments, storing the data fragments to a distributed node, obtaining a predetermined task cooperation strategy, and distributing the task cooperation strategy to an edge computing node in a secret sharing manner; executing safety calculation in a ciphertext state through a task cooperation strategy and the plurality of data fragments, determining a joint motion control instruction of each target robot, and generating corresponding zero-knowledge proof data; and after the verification is passed, the encrypted control instruction is distributed through the block chain smart contract, so that safety calculation of robot cluster collaboration is realized.

The invention discloses an anti-Byzantine privacy protection federated learning method and system based on a block chain. The anti-Byzantine privacy protection federated learning method is realized through the federated learning system comprising a key distribution center, a plurality of clients, two non-collusion servers and a block chain network. According to the method, the data privacy of a client side is guaranteed through a safety calculation process of cooperation of double servers, attacks caused by malicious client sides are reduced as much as possible through a self-adaptive clustering and robustness aggregation method, and reputation values of the client sides are managed through intelligent contracts. The reputation value is used to set the award and penalty obtained after the client participates in federal learning, and the blockchain increases transparency and reliability for the system. And updating the global model based on a security calculation process under a non-collusion double-server architecture, and finally obtaining a safe and reliable global model after training is finished.

The embodiment of the invention relates to the technical field of computer security authentication, in particular to a security authentication method and system based on a secure computer. The method comprises the following steps: carrying out sensing array deployment and data acquisition on a secure computer to obtain calibrated time-space synchronization data; performing temperature and current fusion processing on the calibrated time-space synchronization data to obtain a thermoelectric coupling characteristic spectrum; carrying out point location time sequence correlation analysis on the thermoelectric coupling characteristic spectrum to obtain a point location cross-correlation matrix; performing nonlinear feature extraction on the point location cross-correlation matrix to obtain a nonlinear dynamic feature set; performing dynamic behavior analysis on the nonlinear dynamic feature set to obtain a security calculation behavior dynamic phase spectrum; and performing phase difference calculation on the dynamic phase spectrum of the security calculation behavior to obtain a phase difference vector. According to the method, the early detection capability of threats which are difficult to reproduce and are in a novel hardware level is improved through real-time monitoring and anomaly recognition of computer microcosmic physical characteristics.

A data processing system implements obtaining user prompts s that include instructions to an AI application to perform one or more tasks; storing the user prompts in a prompts datastore in a secure computing environment; analyzing the user prompts using an LLM operating within the secure computing environment to generate normalized prompts based on the user prompts; extracting first n-grams from the normalized prompts using differentially private n-gram extraction that preserves user-level privacy; generating masked normalized prompts by comparing the normalized prompts with the first n-grams and replacing, with a placeholder n-gram, n-grams of the normalized prompts that do not match an n-gram of the first n-grams; extracting second n-grams from the masked normalized prompts using the differentially private n-gram extraction that preserves user-level privacy; outputting the second n-grams from the secure computing environment; and storing the second n-grams in an anonymized prompts datastore outside of the secure computing environment.

The invention discloses a user credit risk assessment method, system, equipment and medium based on multi-industry federated learning in order to improve data security of federated learning, and belongs to the technical field of information. The method comprises the following steps: extracting operator data and bank financial data, and performing encryption preprocessing through a Hash mechanism; performing federated learning on the operator data and the bank financial data after encryption preprocessing, accessing a PSI module as a plug-in to an FATE core, converting RSA of an FATE algorithm into an elliptic curve, and performing secret sharing through a hexagonal grid cellular automaton to obtain a trained federated model; and evaluating the credit risk of the user by using the trained federal model. According to the method, the requirement of hiding a keyword of a queried object or a client ID is met, the hidden query service provides a matched query result, calculation can be carried out without going out data of both parties, and the method follows the data authentication and access process of multi-party security calculation and the overall business process. Data barriers among different industries are broken through, and deep data cooperation of multiple industries is realized.

The invention discloses a multi-modal large model Deepfake detection method based on retrieval enhancement, and relates to the frontier crossing field of artificial intelligence security, computer vision and multi-modal information processing, and the method comprises the steps: 1, carrying out two-stage labeling in sequence, constructing an evidence obtaining knowledge database through the first-stage labeling, constructing an evidence obtaining thinking chain data set through the second-stage labeling, and carrying out the second-stage labeling; wherein the evidence obtaining thinking chain data set is used for generating thinking chain data including a cross validation type, an evidence guide correction type and an adversarial sample type according to the validity of initial judgment and retrieval evidences; step 2, for an image to be detected, retrieving text evidences of Top-k similar cases from the evidence obtaining knowledge database by using a dynamic evidence obtaining retriever; and step 3, inputting an image to be detected and the retrieved text evidence into the critical reasoning multi-modal large model, performing multi-modal reasoning analysis, and outputting a detection result containing a reasoning process.

The invention relates to the technical field of information, in particular to an intelligent storage system with an edge computing and endogenous security mechanism, and aims to solve the problems of security action point lag, high response delay and static resource occupation of the existing security storage technology in an edge computing scene. The system comprises an edge security calculation module, an authentication state machine, a hard wire instruction filtering unit and a controlled instruction execution path, by means of a hardware-level authentication mechanism which is initialized after being powered on, a physical connection gating instruction execution clock and dynamic multiplexing of a security computing buffer area and an I / O memory, 'default rejection 'type endogenous security protection is achieved within microsecond-level delay. According to the invention, a safe vacuum period is effectively eliminated, and high safety, low time delay and efficient utilization of resources are considered.

The invention discloses an identity authentication method based on a secure computer, which relates to the technical field of computer security, and comprises the following steps: deploying an authentication module, and pre-burning an excitation-response pair library of a physical unclonable function; chaotic mapping parameters are randomly initialized, and a chaotic sequence is generated through improved Logistic mapping; sending random excitation to the PUF to obtain an original response, segmenting the original response, and mixing the segmented original response with the chaos sequence; the confusion response is recombined into a three-dimensional matrix, nonlinear diffusion is achieved through a rotation transformation formula, and then the confusion response is flattened into a final registration response; after the user submits a user name, the system generates a random challenge and a current timestamp; calculating a first authentication factor based on the registration response and the timestamp, and recursively generating a factor chain; and the server repeatedly generates a factor chain for matching, updates a registration response if the matching is successful, and triggers a locking mechanism if the matching is failed. According to the chained dynamic authentication method based on PUF response chaos confusion, the dynamic unpredictability of each authentication session can be realized.

The invention discloses an FPGA-oriented hierarchical homomorphic encryption neural network reasoning deployment optimization method, and belongs to the field of neural network optimization and security computing, and the method comprises the following steps: 1, carrying out the adaptive partitioning of an input image, and extracting statistical features; step 2, based on a collaborative fusion optimization normal form, implementing topological pruning of CKKS homomorphic encryption perception on the neural network model; step 3, implementing hierarchical parameter genetic homomorphic encryption on the pruned model: taking a network layer sequence as a link, independently generating encryption parameters in each layer, adaptively generating parameters of a first layer by image block statistical characteristics, and forming an encryption parameter genetic flow by parameters of a subsequent layer through evolutionary genetic tuning of the parameters of the previous layer; and step 4, deploying the optimized model to an FPGA platform to realize efficient privacy protection reasoning. According to the method, the algorithm precision, the homomorphic encryption characteristic and the FPGA hardware performance can be collaboratively optimized, and good performance balance is achieved in a privacy protection scene.

The invention relates to the technical field of supply chain data storage, and discloses a supply chain performance data block chain storage method based on multi-party security computing. The method comprises the following steps: monitoring performance data states and relative interaction relationships of all participants of a supply chain in real time, and judging whether the data density in a target supply chain region exceeds a safety threshold value or not; when a threshold value is exceeded, analyzing the interaction influence of data of each participant through a multi-party security computing protocol, and evaluating the hidden danger of privacy disclosure caused by data sharing; analyzing and processing the spatial and temporal change of the historical performance data by adopting distributed feature learning and combining with a time sequence, and evaluating the potential interference degree of historical data fluctuation on the integrity of the current performance data; and based on the privacy leakage hidden danger and the potential interference degree of historical data fluctuation, whether overall block chain evidence storage optimization of the target supply chain region is carried out is judged. According to the method, the problems of supply chain data density and privacy protection can be solved in a targeted manner, and evidence storage optimization is realized by combining historical data spatial-temporal characteristics.

The codebook-based homomorphic compression system is a novel approach that combines data compression and homomorphic encryption to enable efficient and secure computation on compressed data. It involves quantizing the input data, generating an optimized codebook using techniques like Huffman coding or deep learning, and compressing the data by replacing each value with its corresponding codeword. The compressed data is then encrypted using a homomorphic encryption scheme, such as the Paillier cryptosystem, allowing computations to be performed directly on the encrypted compressed data without decryption. Homomorphic properties of the encryption scheme enable operations like addition and multiplication on the ciphertexts, while preserving the confidentiality of the underlying data. The system also incorporates error correction techniques to mitigate the impact of quantization and encryption on the accuracy of the computations. This approach combines the benefits of data compression and homomorphic encryption, enabling efficient storage, transmission, and secure computation on compressed data.

The invention relates to the technical field of data processing, in particular to an enterprise debtor cross-domain portrait feature extraction method and system combined with multi-party security computing, and the method comprises the steps: obtaining enterprise debtor original data locally stored by participants, connecting the participants to a multi-party security computing system through a security communication channel, and carrying out the cross-domain portrait feature extraction of the multi-party security computing system; the method comprises the following steps of: forming an encryption key pair by a student based on a threshold password, distributing a public key to each participant, keeping a private key by an authorization result user, encrypting original data of each participant by using the public key to obtain encrypted enterprise debtor data, and scoring the importance degree of the encrypted data to obtain an encrypted enterprise debtor; the data with the score higher than a preset threshold value is preferentially selected to execute multi-party security calculation, a multi-dimensional ciphertext portrait feature vector is formed through integration based on a ciphertext calculation result output by a multi-party security calculation protocol, the multi-dimensional ciphertext portrait feature vector is output to an authorization result user, and plaintext portrait features are obtained through decryption by a private key. And efficient extraction and integration of cross-domain features are realized.

Described herein is a technique to update an edge device deployed in a secure computing network. A repository connected to a public network stores build contents configured to update software installed on the edge device; the public network is inaccessible to devices within the secure computing environment. A second device connected to the public network acquires the build contents in a signed lockbox file. An edge device management service generates a lockbox file containing the build contents and a trusted signer outside the secure computing network signs the lockbox file. The second device connects to secure computing network and establishes communications with the edge device. The edge device verifies the signed lockbox file provided by the second device. Upon verification, the edge device extracts the contents of the signed lockbox file and updates the software installed on the edge device. Both offline and online updating approaches are described.

The embodiment of the invention discloses a safety calculation method and device for intelligent workshop device coordination and a medium, and relates to the technical field of safety calculation, and the method comprises the steps: carrying out the on-chain device authentication of a plurality of device terminals in a target intelligent workshop in advance, so as to obtain the device production data corresponding to the target device terminal passing the authentication, performing sensitivity grading on the equipment production data, and determining a corresponding dynamic privacy level; matching a corresponding data encryption strategy according to the dynamic privacy level, determining a plurality of data encryption fragments corresponding to the equipment production data based on the data encryption strategy, and storing the data encryption fragments to a preset distributed node; and obtaining a current collaborative scheduling task of the target intelligent workshop, performing security calculation on the predetermined associated data encryption fragment through a predetermined edge calculation node based on a mixed framework of a confusion circuit and arithmetic secret sharing, generating a collaborative scheduling instruction, and feeding back the collaborative scheduling instruction to the target equipment terminal, therefore, safe calculation of equipment cooperative scheduling is realized.

The invention discloses a production enterprise-oriented information security comprehensive protection system, which comprises a unified security management center, a region boundary protection module, a security computing environment module, a data full life cycle protection module, an authority management module, a threat active defense module and a network security situation awareness module, original dispersed and isolated safety capabilities are integrated into a linkage system through an integrated architecture of a unified safety management center and six functional modules through a unified interface / event bus, so that instant isolation and authentication of a transverse production control area, a management information area and a longitudinal remote operation and maintenance channel are realized, and the transverse penetration blocking rate is remarkably improved; role isolation and dynamic authorization are realized through the authority management module, the attack surface of a supply chain is greatly narrowed, the manual operation and maintenance workload is reduced by about six percent, and the overall safety toughness and operation efficiency of an enterprise are remarkably improved.

The invention relates to the technical field of quantum security computing communication, and discloses a cluster state-based third-party quantum summation method with a bidirectional identity authentication mechanism, which comprises the following steps of: firstly, realizing bidirectional identity authentication between a participant and a third party in a quantum channel by pre-sharing secret identity information and a hash function in combination with a decoy photon technology; and impersonation and man-in-the-middle attack are fundamentally eradicated. And after the authentication is passed, the participant randomly executes measurement or reflection operation on the particle to which the participant belongs, so that an encrypted private key can be generated under the assistance of a third party, and external eavesdropping and internal participant attack can be jointly detected according to an operation combination to form multi-level security protection. Finally, the third party can only calculate the bitwise modular binary sum of the private bit string of each party, and cannot obtain any single input value. According to the method, authentication and calculation are organically fused, unconditional security is guaranteed, and meanwhile, the quantum capability requirements of participants are remarkably reduced.

This disclosure is directed to a method comprising: initiating a first application, a second application, and a third application, which are associated with a secure computing network; routing a first computing input, a second computing input, and third computing input, respectively, to the first application, the second application and the third application; executing, using the first application and based on the first computing input, a first computing operation and thereby generating a first local computing result; executing, using the second application, based on the second computing input, a second computing operation and thereby generating a second local computing result; and executing, using the third application, based on the third computing input, a third computing operation and thereby generating a third local computing result. The method also includes leveraging the first local computing result, the second local computing result, and third local computing result to generate network resolution data.