6 papers
An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses
Hao Liang, Wanrong Zhang, Xinlei He +2
Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to protect sensitive data during the training of machine learning models, but its privacy guarantee often…
Estimating Privacy Leakage of Augmented Contextual Knowledge in Language Models
James Flemings, Bo Jiang, Wanrong Zhang +2
Language models (LMs) rely on their parametric knowledge augmented with relevant contextual knowledge for certain tasks, such as question answering. However, the contextual knowled…
Interpreting Differential Privacy in Terms of Disclosure Risk
Zeki Kazan, Sagar Sharma, Wanrong Zhang +2
As the use of differential privacy (DP) becomes widespread, the development of effective tools for reasoning about the privacy guarantee becomes increasingly critical. In pursuit o…
TokenShapley: Token Level Context Attribution with Shapley Value
Yingtai Xiao, Yuqing Zhu, Sirat Samyoun +3
Large language models (LLMs) demonstrate strong capabilities in in-context learning, but verifying the correctness of their generated responses remains a challenge. Prior work has…
When Focus Enhances Utility: Target Range LDP Frequency Estimation and Unknown Item Discovery
Bo Jiang, Wanrong Zhang, Donghang Lu +2
Local Differential Privacy (LDP) protocols enable the collection of randomized client messages for data analysis, without the necessity of a trusted data curator. Such protocols ha…
Meeting Utility Constraints in Differential Privacy: A Privacy-Boosting Approach
Bo Jiang, Wanrong Zhang, Donghang Lu +3
Data engineering often requires accuracy (utility) constraints on results, posing significant challenges in designing differentially private (DP) mechanisms, particularly under str…