3 papers
cs.CR2026
MemHunter: Automated and Verifiable Memorization Detection at Dataset-scale in LLMs
Zhenpeng Wu, Jian Lou, Zibin Zheng +1
Large language models (LLMs) have been shown to memorize and reproduce content from their training data, raising significant privacy concerns, especially with web-scale datasets. E…
cs.LG2025
ParaAegis: Parallel Protection for Flexible Privacy-preserved Federated Learning
Zihou Wu, Yuecheng Li, Tianchi Liao +2
Federated learning (FL) faces a critical dilemma: existing protection mechanisms like differential privacy (DP) and homomorphic encryption (HE) enforce a rigid trade-off, forcing a…
cs.LG2025
Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off
Yuecheng Li, Lele Fu, Tong Wang +6
To defend against privacy leakage of user data, differential privacy is widely used in federated learning, but it is not free. The addition of noise randomly disrupts the semantic…