by jingnan zheng Papers
2 papers found
Conference
RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards
jingnan zheng, Xiangtian Ji, Yijun Lu et al.
NEURIPS 2025arXiv:2506.07736
11
citations
Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
Chenhang Cui, Gelei Deng, An Zhang et al.
NEURIPS 2025arXiv:2411.11496
4
citations