User-level member reasoning method based on generative adversarial network

Abstract

The invention discloses a user-level member reasoning scheme based on a federated learning environment. A GANs (Generative Adversarial Networks) method is adopted to acquire data distribution so as tostart member reasoning. In a federated learning environment, an attacker initiates a member reasoning attack without accessing user data to deduce whether a given data record belongs to a target training set so as to steal data privacy of a target data set. The method comprises the following steps: 1) user-level member reasoning: a malicious user initiates a member reasoning attack to steal member privacy of a specific user, and further reveals safety vulnerabilities of current joint learning; and 2) performing data expansion by using a locally deployed generative adversarial network so as toobtain data distribution of other users. The effectiveness of the attack method provided by the invention is fully considered under the condition that the user data has multiple tags.

Description

technical field [0001] The invention relates to the field of artificial intelligence security, in particular to a user-level member reasoning method based on a generative confrontation network. Background technique [0002] With the decentralized development of machine learning, research on federated learning techniques is increasing. In federated learning, multiple users participate in the training process of the model. All users update the global model by summarizing their own training parameters, and keep all training data locally. Although federated learning can provide basic privacy guarantees through local training, there are still privacy issues in the process of parameter aggregation and communication with federated models, and many attack methods including membership inference attacks have undermined the security of federated learning. Fundamentally, the membership inference problem is a classification problem, where an attacker needs to determine whether data of u...

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: In order to solve the problems existing in existing member reasoning, the purpose of the present invention is to provide a user-level member reasoning method based on generative confrontation network, which can further reveal the current federated member reasoning method based on user privacy data in a federated learning environment. Learned Security Vulnerabilities

Images