3 papers
cs.CR2025
BudgetLeak: Membership Inference Attacks on RAG Systems via the Generation Budget Side Channel
Hao Li, Jiajun He, Guangshuo Wang +3
Retrieval-Augmented Generation (RAG) enhances large language models by integrating external knowledge, but reliance on proprietary or sensitive corpora poses various data risks, in…
cs.CR2024
Model Hijacking Attack in Federated Learning
Zheng Li, Siyuan Wu, Ruichuan Chen +6
Machine learning (ML), driven by prominent paradigms such as centralized and federated learning, has made significant progress in various critical applications ranging from autonom…
cs.CR2024
SeqMIA: Sequential-Metric Based Membership Inference Attack
Hao Li, Zheng Li, Siyuan Wu +5
Most existing membership inference attacks (MIAs) utilize metrics (e.g., loss) calculated on the model's final state, while recent advanced attacks leverage metrics computed at var…