4 papers
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…
MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning
Yizhe Zeng, Wei Zhang, Yunpeng Li +3
While Chain-of-Thought (CoT) prompting has become a standard paradigm for eliciting complex reasoning capabilities in Large Language Models, it inadvertently exposes a new attack s…
LungCURE: Benchmarking Multimodal Real-World Clinical Reasoning for Precision Lung Cancer Diagnosis and Treatment
Fangyu Hao, Jiayu Yang, Yifan Zhu +14
Lung cancer clinical decision support demands precise reasoning across complex, multi-stage oncological workflows. Existing multimodal large language models (MLLMs) fail to handle…
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…