3 papers
cs.SI2023
Privacy-Preserving Individual-Level COVID-19 Infection Prediction via Federated Graph Learning
Wenjie Fu, Huandong Wang, Chen Gao +3
Accurately predicting individual-level infection state is of great value since its essential role in reducing the damage of the epidemic. However, there exists an inescapable risk…
cs.CL2023
Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
Wenjie Fu, Huandong Wang, Chen Gao +3
Membership Inference Attacks (MIA) aim to infer whether a target data record has been utilized for model training or not. Existing MIAs designed for large language models (LLMs) ca…
cs.LG2023
A Probabilistic Fluctuation based Membership Inference Attack for Diffusion Models
Wenjie Fu, Huandong Wang, Liyuan Zhang +3
Membership Inference Attack (MIA) identifies whether a record exists in a machine learning model's training set by querying the model. MIAs on the classic classification models hav…