1 citations · 1 across the 13 of their papers we have counts for
8 papers · 1 filter
Tight Privacy Audit in One Run
Zihang Xiang, Tianhao Wang, Hanshen Xiao +2
In this paper, we study the problem of privacy audit in one run and show that our method achieves tight audit results for various differentially private protocols. This includes ob…
Beyond Ordinary Lipschitz Constraints: Differentially Private Stochastic Optimization with Tsybakov Noise Condition
Difei Xu, Meng Ding, Zihang Xiang +2
We study Stochastic Convex Optimization in the Differential Privacy model (DP-SCO). Unlike previous studies, here we assume the population risk function satisfies the Tsybakov Nois…
FlashDP: Private Training Large Language Models with Efficient DP-SGD
Liangyu Wang, Junxiao Wang, Jie Ren +3
As large language models (LLMs) increasingly underpin technological advancements, the privacy of their training data emerges as a critical concern. Differential Privacy (DP) serves…
Differentially Private Sparse Linear Regression with Heavy-tailed Responses
Xizhi Tian, Meng Ding, Touming Tao +2
As a fundamental problem in machine learning and differential privacy (DP), DP linear regression has been extensively studied. However, most existing methods focus primarily on eit…
Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness
Cheng-Long Wang, Qi Li, Zihang Xiang +2
Growing concerns over data privacy and security highlight the importance of machine unlearning--removing specific data influences from trained models without full retraining. Techn…
Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax Optimization
Ruijia Zhang, Mingxi Lei, Meng Ding +3
In this paper, we study the problem of (finite sum) minimax optimization in the Differential Privacy (DP) model. Unlike most of the previous studies on the (strongly) convex-concav…
Towards User-level Private Reinforcement Learning with Human Feedback
Jiaming Zhang, Mingxi Lei, Meng Ding +5
Reinforcement Learning with Human Feedback (RLHF) has emerged as an influential technique, enabling the alignment of large language models (LLMs) with human preferences. Despite th…
Privacy Audit as Bits Transmission: (Im)possibilities for Audit by One Run
Zihang Xiang, Tianhao Wang, Di Wang
Auditing algorithms' privacy typically involves simulating a game-based protocol that guesses which of two adjacent datasets was the original input. Traditional approaches require…