Defending Against Gradient Inversion Attacks for Biomedical Images via Learnable Data Perturbation
The increasing need for sharing healthcare data and collaborating on clinical research has raised privacy concerns. Health information leakage due to malicious attacks can lead to serious problems such as misdiagnoses and patient identification issues. Privacy-preserving machine learning (PPML) and privacy-enhancing technologies, particularly federated learning (FL), have emerged in recent years as innovative solutions to balance privacy protection with data utility; however, they also suffer from inherent privacy vulnerabilities. Gradient inversion attacks constitute major threats to data sharing in federated learning. Researchers have proposed many defenses against gradient inversion attacks. However, current defense methods for healthcare data lack generalizability, i.e., existing solutions may not be applicable to data from a broader range of populations. In addition, most existing defense methods are tested using non-healthcare data, which raises concerns about their applicability to real-world healthcare systems. In this study, we present a defense against gradient inversion attacks in federated learning. We achieve this using latent data perturbation and minimax optimization, utilizing both general and medical image datasets. Our method is compared to two baselines, and the results show that our approach can outperform the baselines with a reduction of 12.5% in the attacker's accuracy in classifying reconstructed images. The proposed method also yields an increase of over 12.4% in Mean Squared Error (MSE) between the original and reconstructed images at the same level of model utility of around 90% client classification accuracy. The results suggest the potential of a generalizable defense for healthcare data.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningPrivacy PreservingSimilar Papers 제목 키워드 기반
Adversarially Robust Classification by Conditional Generative Model Inversion
Most adversarial attack defense methods rely on obfuscating gradients. These methods are successful in defending against gradient-based attacks; however, they are easily circumvented by attacks which either do not use th…
Adversarial AttackClassificationmodelRobust classificationPurifier: Defending Data Inference Attacks via Transforming Confidence Scores
Neural networks are susceptible to data inference attacks such as the membership inference attack, the adversarial model inversion attack and the attribute inference attack, where the attacker could infer useful informat…
AttributeInference AttackMembership Inference AttackRevisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks
Collaborative learning (CL) is a distributed learning framework that aims to protect user privacy by allowing users to jointly train a model by sharing their gradient updates only. However, gradient inversion attacks (GI…
Understanding Deep Gradient Leakage via Inversion Influence Functions
Deep Gradient Leakage (DGL) is a highly effective attack that recovers private training images from gradient vectors. This attack casts significant privacy challenges on distributed learning from clients with sensitive d…
Defending Label Inference Attacks in Split Learning under Regression Setting
As a privacy-preserving method for implementing Vertical Federated Learning, Split Learning has been extensively researched. However, numerous studies have indicated that the privacy-preserving capability of Split Learni…
Federated LearningPrivacy PreservingregressionVertical Federated Learning