Quantifying and Localizing Usable Information Leakage from Neural Network Gradients
In collaborative learning, clients keep their data private and communicate only the computed gradients of the deep neural network being trained on their local data. Several recent attacks show that one can still extract private information from the shared network's gradients compromising clients' privacy. In this paper, to quantify the private information leakage from gradients we adopt usable information theory. We focus on two types of private information: original information in data reconstruction attacks and latent information in attribute inference attacks. Furthermore, a sensitivity analysis over the gradients is performed to explore the underlying cause of information leakage and validate the results of the proposed framework. Finally, we conduct numerical evaluations on six benchmark datasets and four well-known deep models. We measure the impact of training hyperparameters, e.g., batches and epochs, as well as potential defense mechanisms, e.g., dropout and differential privacy. Our proposed framework enables clients to localize and quantify the private information leakage in a layer-wise manner, and enables a better understanding of the sources of information leakage in collaborative learning, which can be used by future studies to benchmark new attacks and defense mechanisms.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeSimilar Papers 제목 키워드 기반
Layer-wise Characterization of Latent Information Leakage in Federated Learning
Training deep neural networks via federated learning allows clients to share, instead of the original data, only the model trained on their data. Prior work has demonstrated that in practice a client's private informatio…
Federated LearningGradients Stand-in for Defending Deep Leakage in Federated Learning
Federated Learning (FL) has become a cornerstone of privacy protection, shifting the paradigm towards localizing sensitive data while only sending model gradients to a central server. This strategy is designed to reinfor…
Federated LearningReal-Time Privacy Risk Measurement with Privacy Tokens for Gradient Leakage
The widespread deployment of deep learning models in privacy-sensitive domains has amplified concerns regarding privacy risks, particularly those stemming from gradient leakage during training. Current privacy assessment…
Adversarial AttackDo Gradient Inversion Attacks Make Federated Learning Unsafe?
Federated learning (FL) allows the collaborative training of AI models without needing to share raw data. This capability makes it especially interesting for healthcare applications where patient and data privacy is of u…
Federated LearningPrivacy PreservingA Quantitative Metric for Privacy Leakage in Federated Learning
In the federated learning system, parameter gradients are shared among participants and the central modulator, while the original data never leave their protected source domain. However, the gradient itself might carry e…
Federated LearningMutual Information Estimation