2 papers
cs.CR2026
Low Rank Comes with Low Security: Gradient Assembly Poisoning Attacks against Distributed LoRA-based LLM Systems
Yueyan Dong, Minghui Xu, Qin Hu +5
Low-Rank Adaptation (LoRA) has become a popular solution for fine-tuning large language models (LLMs) in federated settings, dramatically reducing update costs by introducing train…
cs.CR2025
Unveiling Malware Patterns: A Self-analysis Perspective
Fangtian Zhong, Qin Hu, Yili Jiang +2
The widespread usage of Microsoft Windows has unfortunately led to a surge in malware, posing a serious threat to the security and privacy of millions of users. In response, the re…