Learning Robust and Privacy-Preserving Representations via Information Theory
Machine learning models are vulnerable to both security attacks (e.g., adversarial examples) and privacy attacks (e.g., private attribute inference). We take the first step to mitigate both the security and privacy attacks, and maintain task utility as well. Particularly, we propose an information-theoretic framework to achieve the goals through the lens of representation learning, i.e., learning representations that are robust to both adversarial examples and attribute inference adversaries. We also derive novel theoretical results under our framework, e.g., the inherent trade-off between adversarial robustness/utility and attribute privacy, and guaranteed attribute privacy leakage against attribute inference adversaries.
Code (1)
Tasks
Adversarial RobustnessAttributePrivacy PreservingRepresentation LearningSimilar Papers 제목 키워드 기반
Privacy Preserving Optics for Miniature Vision Sensors
The next wave of micro and nano devices will create a world with trillions of small networked cameras. This will lead to increased concerns about privacy and security. Most privacy preserving algorithms for computer visi…
Face RecognitionPrivacy PreservingPrivacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective
Learning with graphs has attracted significant attention recently. Existing representation learning methods on graphs have achieved state-of-the-art performance on various graph-related tasks such as node classification,…
Link PredictionNode ClassificationPrivacy PreservingRepresentation LearningLearning data-derived privacy preserving representations from information metrics
It is clear that users should own and control their data and privacy. Utility providers are also becoming more interested in guaranteeing data privacy. Therefore, users and providers can and should collaborate in privacy…
AttributeFace RecognitionPrivacy PreservingBlindU: Blind Machine Unlearning without Revealing Erasing Data
Machine unlearning enables data holders to remove the contribution of their specified samples from trained models to protect their privacy. However, it is paradoxical that most unlearning methods require the unlearning r…
Federated LearningToward Privacy and Utility Preserving Image Representation
Face images are rich data items that are useful and can easily be collected in many applications, such as in 1-to-1 face verification tasks in the domain of security and surveillance systems. Multiple methods have been p…
Face VerificationPrivacy Preserving