Differential Privacy

Differential privacy (DP) is a rigorous framework for ensuring data privacy in machine learning by adding carefully calibrated noise to model training processes. Current research focuses on improving the accuracy of DP models, particularly for large-scale training, through techniques like adaptive noise allocation, Kalman filtering for noise reduction, and novel gradient processing methods. This active area of research is crucial for enabling the responsible use of sensitive data in various applications, ranging from healthcare and finance to natural language processing and smart grids, while maintaining strong privacy guarantees.

Papers

March 5, 2022

The Impact of Differential Privacy on Group Disparity Mitigation
Victor Petrén Bach Hansen, Atula Tejaswi Neerkaje, Ramit Sawhney, Lucie Flek, Anders Søgaard
Differential Privacy Global Impact Procedural Fairness Empirical Risk Minimization Private Model Group Disparity Mitigating Disparity

March 4, 2022

Differentially Private Label Protection in Split Learning
Xin Yang, Jiankai Sun, Yuanshun Yao, Junyuan Xie, Chong Wang
Differential Privacy Split Learning Private Label

March 2, 2022

February 25, 2022

Does Label Differential Privacy Prevent Label Inference Attacks?
Ruihan Wu, Jin Peng Zhou, Kilian Q. Weinberger, Chuan Guo
Differential Privacy Private Machine Learning Label Inference Attack Private Label

February 24, 2022

February 21, 2022

Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guarantees
Franziska Boenisch, Christopher Mühl, Roy Rinberg, Jannis Ihrig, Adam Dziedzic
Differential Privacy Privacy Guarantee Private Machine Learning Privacy Utility Trade User Configurable Privacy Defense

February 20, 2022

Collusion Resistant Federated Learning with Oblivious Distributed Differential Privacy
David Byrd, Vaikkunth Mugunthan, Antigoni Polychroniadou, Tucker Hybinette Balch
Differential Privacy Federated Learning Privacy Mechanism Tacit Collusion

February 18, 2022

February 16, 2022

February 15, 2022

Differential Privacy

Papers

The Impact of Differential Privacy on Group Disparity Mitigation

Differentially Private Label Protection in Split Learning

Label Leakage and Protection from Forward Embedding in Vertical Federated Learning

GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation

Does Label Differential Privacy Prevent Label Inference Attacks?

Bounding Membership Inference

Debugging Differential Privacy: A Case Study for Privacy Auditing

How reparametrization trick broke differentially-private text representation learning

Differentially Private Estimation of Heterogeneous Causal Effects

Quantum Differential Privacy: An Information Theory Perspective

Differential Secrecy for Distributed Data and Applications to Robust Differentially Secure Vector Summation

Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guarantees

Collusion Resistant Federated Learning with Oblivious Distributed Differential Privacy

FedEmbed: Personalized Private Federated Learning

Differentially Private Federated Learning via Inexact ADMM with Multiple Local Updates

Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams

Contextualize differential privacy in image database: a lightweight image differential privacy approach based on principle component analysis inverse

Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey

Defending against Reconstruction Attacks with R\'enyi Differential Privacy

Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacy