Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
CNT: Safety-oriented Function Reuse across LLMs via Cross-Model Neuron Transfer
Yue Zhao, Yujia Gong, Ruigang Liang +4
The widespread deployment of large language models (LLMs) calls for post-hoc methods that can flexibly adapt models to evolving safety requirements. Meanwhile, the rapidly expandin…
cs.CR2024
Membership Information Leakage in Federated Contrastive Learning
Kongyang Chen, Wenfeng Wang, Zixin Wang +3
Federated Contrastive Learning (FCL) represents a burgeoning approach for learning from decentralized unlabeled data while upholding data privacy. In FCL, participant clients colla…