2 papers
cs.CR2026
Why Are LLM Backdoor Defenses Fragmented? A Feature-Level Explanation with Sparse Autoencoders
Yizhe Zeng, Chenxu Niu, Wei Zhang +7
Backdoor attacks pose a serious threat to large language models (LLMs), but existing defenses remain fragmented, failing to pro?vide unified defense against both dirty-label and cl…
cs.SE2025
QLPro: Automated Code Vulnerability Discovery via LLM and Static Code Analysis Integration
Junze Hu, Xiangyu Jin, Yizhe Zeng +5
We introduce QLPro, a vulnerability detection framework that systematically integrates LLMs and static analysis tools to enable comprehensive vulnerability detection across entire…