作者位次 #4/6ACL 2026Poster· Natural Language Processing
Safe- F ed LLM : Delving into the Safety of Federated Large Language Models
Mingxiang Tao · Yu Tian · Wenxuan Tu · Yue Yang · Xue Yang · Xiangyan Tang
摘要
Federated learning (FL) addresses privacy and data-silo issues in the training of large language models (LLMs). Most prior work focuses on improving the efficiency of federated learning for LLMs (FedLLM). However, security in open federated environments, particularly defenses against malicious cl...