2 papers
cs.LG2026
Attributing and Exploiting Safety Vectors through Global Optimization in Large Language Models
Fengheng Chu, Jiahao Chen, Yuhong Wang +4
While Large Language Models (LLMs) are aligned to mitigate risks, their safety guardrails remain fragile against jailbreak attacks. This reveals limited understanding of components…
cs.CR2026
Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models
Songze Li, Ruishi He, Xiaojun Jia +2
Large Language Models (LLMs) face a significant threat from multi-turn jailbreak attacks, where adversaries progressively steer conversations to elicit harmful outputs. However, th…