15results about How to "Protect private information" patented technology

The invention discloses a multi-virtual power plant energy carbon transaction price determination method and system based on a master-slave game. The method comprises the following steps: determining a master-slave game framework between a power distribution system operator and a plurality of virtual power plants; based on a master-slave game framework, a double-layer optimization model of energy and carbon sharing of the multiple virtual power plants is established, the upper layer of the double-layer optimization model is a dynamic pricing model with the purpose of maximizing the income of a power distribution system operator, and the lower layer of the double-layer optimization model is an energy management model with the purpose of minimizing the operation cost of the virtual power plants; and establishing a double-layer Kriging meta-model taking the transaction electricity price and the carbon price as inputs and the transaction electricity quantity and the carbon quota quantity as outputs, fitting and replacing the energy management model of the double-layer optimization model by adopting the double-layer Kriging meta-model, and solving to obtain a global optimal solution. According to the method, sharing and circulation of energy and carbon quotas among virtual power plants are effectively promoted, the economic and environmental benefits are improved, and the privacy security of each subject can be protected.

The application discloses a building group internal electric energy mutual aid scheduling and distribution method considering user limited rational behavior and multi-dimensional contribution degree, and the method corrects the actual callable boundary of building flexible resources by constructing user multi-dimensional portrait parameters, limited rational utility functions and response probability models; based on a building group internal P2P electric energy mutual aid model, an asymmetric Nash bargaining model and a multi-dimensional contribution degree income distribution model, two-stage ADMM distributed solution is adopted to solve internal mutual aid electric quantity and settlement electricity price, and the executable scheduling of the building group internal electric energy mutual aid and the cooperative residual fair distribution are realized.

The present application provides an information security level protection optimization method and system. The data provider performs system initialization, generates a public key and a master key, and generates a private key and an access control policy based on the public key, the master key and the access attributes corresponding to each authorized user, sends the private key to the corresponding authorized user, sends the data set and the encryption parameter to the data server, and sends the access control policy to the verification server; the user terminal generates a user access credential based on the private key and the public key, and sends an access request carrying the user access credential to the verification server; the verification server performs verification, and denies access if the verification fails, and sends the access request to the data server if the verification passes; the data server establishes a one-way channel with the user terminal, encrypts the data using the encryption parameters and transmits it to the user terminal in one direction; the user terminal decrypts the received encrypted data. Thus, fine-grained access control is achieved, scalability is improved, and data security is guaranteed at the same time.

This invention discloses a federated learning method based on group signatures, smart contracts, and a distributed file system (DFS) to hide data source information, relating to the field of computer cryptography. This invention utilizes smart contracts to manage members of each group. Each group member completes model training using its local data to obtain model parameters. These parameters are then encrypted using group signatures and uploaded to the DFS to obtain the DFS address. The encryption key and DFS address are then encrypted and group-signed again via a smart contract and uploaded. The central server decrypts the DFS address and key to obtain the DFS address, downloads the encrypted model parameters from the DFS, and decrypts them using the key to obtain the model parameters uploaded by each group member. These parameters are then aggregated and updated to obtain the improved global model. This invention effectively protects the privacy of data providers, ensuring the protection of data source information for both parties during the federated learning process.

The application discloses a kind of multi-source big data acquisition and pre-processing database construction method and system, it is related to database technical field, the present application completes multi-source heterogeneous data acquisition using edge-center two-level distributed architecture, and the security of data transmission is guaranteed by transmission encryption and integrity check mechanism, hierarchical pre-processing is carried out to data to realize heterogeneous data semantic alignment and multidimensional fusion;Distributed hybrid storage architecture is constructed, adaptive database index mechanism is set, and through multidimensional data quality evaluation, the incremental update and full-amount synchronization of database are realized.The present application can realize the unified collection of various source data, standardized processing, effectively break the data island barrier, significantly improve data processing efficiency and storage running performance, and stably guarantee the overall data quality and data consistency of database.

The present invention discloses a federated learning method and system based on image privacy protection of a large model computing network, obtains node information of an image computing network and node processing image data information, divides nodes into passive nodes and active nodes according to the node information and node processing image data information, and prevents active nodes from inferring feature information of passive nodes through intermediate results of passive nodes and global module gradients of passive nodes by encrypting and protecting the intermediate results of passive nodes and global module gradients of passive nodes; and prevents passive nodes from inferring labels of active nodes through the gradients of total outputs of active nodes by encrypting and protecting the gradients of total outputs of active nodes. The present invention can solve the technical problems of malicious passive nodes stealing labels of active nodes through global modules or gradients and active nodes stealing features of passive nodes through the outputs of global modules of passive nodes.

The invention relates to the technical field of federated learning model reliable training and safe aggregation, in particular to an attack detection and defense method for a federated learning model in a mobile scene, which comprises the following steps: using a block chain to store equipment information, and finishing selection of federated learning users by a server under the condition that the server is not in contact with equipment; the equipment judges the authenticity of the received training task by using a zero-knowledge proof method; the equipment performs encryption transmission on the local model by using the proving key to resist model parameter reasoning attack; and the block chain verifies the validity of the local model by using the verification key and the Pearson commitment, so that the safe aggregation of the federal learning global model is realized. The method has the advantages of being high in attack detection speed, few in needed communication and computing resources and low in algorithm complexity.

This application provides a method, apparatus, device, medium, and program product for security detection of application behavior, relating to the financial technology field. It includes: based on the startup status of a banking application installed on a terminal device under test, in a trusted execution environment corresponding to the security chip of the terminal device, real-time collection of sensitive behavior data of the banking application; in the trusted execution environment, risk analysis processing of the sensitive behavior data is performed based on the historical usage data of the banking application corresponding to the terminal device to determine the risk category of the sensitive behavior data; based on the risk category, a security report for the banking application is generated, and a security report generation prompt is displayed; in response to the user's viewing operation of the prompt, abnormal behavior verification is performed on the terminal device and the banking application in the trusted execution environment; if the verification is successful, the security report is de-identified to obtain and display a de-identified security report. The method of this application improves the security of application behavior detection.

The present invention discloses a privacy-protected task offloading method and system in a vehicle formation, comprising: a pilot vehicle divides a task into multiple subtasks, signs a task request and broadcasts it to all following vehicles; the following vehicles calculate the time required to execute the subtasks, generate task parameters and encrypt and return them to the pilot vehicle; the pilot vehicle summarizes the task parameters of all following vehicles and forwards them to a first cloud server CSA ; First Cloud Server CSA and the second cloud server CSB The task execution time is encrypted and compared to determine the most suitable vehicle to execute each subtask; the pilot vehicle distributes the specific task content to each designated follower vehicle; each designated follower vehicle signs and encrypts the specific task result and sends it to the pilot vehicle, which verifies the signature and decrypts the result. The technical solution of the present invention improves the efficiency and security of task offloading while ensuring the privacy of the vehicle and the task content.

The invention discloses a construction method of a brain-computer interface decoding model and an electroencephalogram signal recognition method, and belongs to the technical field of electroencephalogram detection.The construction method of the brain-computer interface decoding model comprises the steps that firstly, alignment operation is executed on electroencephalogram samples in an original calibration set of a target domain, and the accuracy of cross-user migration is improved; enhancing each electroencephalogram sample in the alignment calibration set to obtain a target data set, so that the generalization ability of the model can be improved; carrying out adversarial training on the initial brain-computer interface decoding model by utilizing adversarial samples generated by each electroencephalogram sample X in the target data set under a plurality of different random seeds to obtain an updated brain-computer interface decoding model corresponding to each random seed, and keeping high robustness of the model when facing the adversarial samples and noise data; and integrating the updated brain-computer interface decoding models corresponding to the random seeds to obtain a target brain-computer interface decoding model, thereby effectively improving the classification accuracy and antagonism robustness.

The present invention discloses a privacy protection database JOIN type query method, system and device based on homomorphic secret sharing. The method includes a setting stage and a query stage. In the setting stage, a Paillier encrypted public key N, a private key d and an encrypted private key E(d) are generated, and then packaged and sent to the client; in the query stage, the client sends the encrypted client table to the cloud server, and the query task is executed according to the queryer's instruction; the cloud server uses the homomorphic secret sharing private key ek to query the client table. i , the encrypted value I in the encrypted customer table x The local data is converted into secret shares, and the cloud servers obtain their own secret share tables; each cloud server executes a secure connection protocol based on the encrypted customer table and secret share table it possesses, and obtains the secret shares of the connection table respectively; the inquirer reconstructs the connection table based on the secret shares of each connection table. The present invention combines the characteristics of oblivious sorting and homomorphic secret sharing to design a secure connection protocol, thereby avoiding the communication overhead in the matching stage.

The present invention proposes a browser fingerprint defense method, electronic device and storage medium based on the leakage of hidden plug-in CSS, which belongs to the technical field of browser fingerprint defense. The method includes the following steps: S1. Collect and refine the CSS of the plug-in and save it locally; S2. Control the CSS introduced by the hidden or displayed installed plug-in to the web page, and the CSS introduced by the installed plug-in to the web page includes hiding of layout-irrelevant attributes and hiding of layout-related attributes. S3. Complete the randomization of the plug-in. The present invention can not only hide our real installed plug-in information, but also resist browser fingerprint recognition and protect the user's privacy information. By randomly installing the plug-in, it can actively resist the website from collecting the plug-in as fingerprint information; it solves the technical problems of low flexibility, poor performance and weak defense of the fingerprint defense method in the prior art.

The invention provides a flexible adjustment unit data transmission method for a smart power grid, and belongs to the technical field of power grid management. The flexible adjusting unit data transmission method for the smart power grid comprises the following steps: acquiring electric energy parameters of a special transformer user in real time, wherein the electric energy parameters comprise split-phase voltage, current, active power, a power factor and frequency; performing edge calculation processing on the electric energy parameters to formulate a load prediction strategy, a load identification strategy, an electric energy quality monitoring strategy and a flexible regulation and control strategy; and reporting the processed electric energy parameters to an interactive management master station in an encrypted communication mode. According to the flexible adjustment unit data transmission method for the smart power grid, the security of data transmission can be guaranteed, load fine management, power quality optimization and dynamic adjustment capability enhancement of the smart power grid are realized, and the stability of a power grid system is maintained.

The invention discloses a privacy protection image feature compression method and a privacy protection image feature compression system for edge cloud collaborative reasoning, which are based on a novel privacy protection feature compression framework, are combined with an attention mechanism, and guide the compression of intermediate features through an adversarial collaborative training strategy in a feature domain set. Selective aggregation and feature disturbance suppression of a feature domain are introduced into a feature domain focused confrontation cooperative training strategy, the security and anti-attack ability of data in the transmission process are enhanced, and the risk that data privacy is leaked on a cloud honest but curious server is effectively reduced. In order to improve the generalization ability and adaptability of the algorithm, system evaluation is carried out on a plurality of image data sets and different deep learning models. Experimental results show that the method is remarkably superior to an existing feature compression method in the aspects of intermediate feature transmission efficiency, analysis precision and privacy protection level, and powerful technical support is provided for application of a large-scale deep learning model in a resource-limited edge device environment.

The invention provides a member archive encryption management method, which comprises the following steps of: S11, performing encryption judgment on a received member archive, and if the encryption state is unencrypted, executing a next step on the member archive; s12, generating an encryption key for a member file needing to be encrypted through a chaos sequence; s13, performing pixel point conversion on the text data to obtain a text image; s14, performing encryption processing on the image data and the text image through a chaotic encryption algorithm to obtain a final encrypted image, and storing the final encrypted image to a corresponding file in a protection system; and S15, receiving a query request sent by the member equipment, judging whether the member identity information is consistent with preset registration information, and if so, restoring the encrypted member file. According to the invention, after the member archive is encrypted based on the chaos encryption algorithm, the text data and the image data in the member archive are encrypted, so that the security and the integrity of the encrypted member archive and the data in the archive are ensured.