3 papers
cs.CR2025
The Art of Hide and Seek: Making Pickle-Based Model Supply Chain Poisoning Stealthy Again
Tong Liu, Guozhu Meng, Peng Zhou +3
Pickle deserialization vulnerabilities have persisted throughout Python's history, remaining widely recognized yet unresolved. Due to its ability to transparently save and restore…
cs.CR2025
Bleeding Pathways: Vanishing Discriminability in LLM Hidden States Fuels Jailbreak Attacks
Yingjie Zhang, Tong Liu, Zhe Zhao +2
LLMs remain vulnerable to jailbreak attacks that exploit adversarial prompts to circumvent safety measures. Current safety fine-tuning approaches face two critical limitations. Fir…
cs.LG2025
Understanding and Enhancing the Transferability of Jailbreaking Attacks
Runqi Lin, Bo Han, Fengwang Li +1
Jailbreaking attacks can effectively manipulate open-source large language models (LLMs) to produce harmful responses. However, these attacks exhibit limited transferability, faili…