From ``Sure" to ``Sorry": Detecting Jailbreak in Large Vision Language Model via JailNeurons
Yuyou Gan · Qingming Li · Junhao Li · Zhi Chen · Jinbao Li · Xiaoming Li · Shouling Ji
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Yuyou Gan · Qingming Li · Junhao Li · Zhi Chen · Jinbao Li · Xiaoming Li · Shouling Ji
Naen Xu · Jiayi Sheng · Changjiang Li · Chunyi Zhou · Yuyuan Li · Tianyu Du · Jun Wang · Zhihui Fu · Jinbao Li · Shouling Ji
Puns are a common form of rhetorical wordplay that exploits polysemy and phonetic similarity to create humor. In multimodal puns, visual and textual elements synergize to ground the literal sense and evoke the figurative meaning simultaneously. Although Vision-Language Models (VLMs) are widely us...
Rui Yin · Tianxu Han · Naen Xu · Changjiang Li · Ping He · Chunyi Zhou · Jun Wang · Zhihui Fu · Tianyu Du · Jinbao Li · Shouling Ji
Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines, yet this deployment also enlarges the supply-chain attack surface: adversaries can distribute backdoored checkpoints that behave normally under standard evaluation but jailbreak when a hidden trigger is...
Hengyu An · Minxi Li · Naen Xu · Chunyi Zhou · Xiaogang Xu · Tianyu Du · Jinbao Li · Shouling Ji
Self-evolving agents achieve personalization by accumulating user-specific memories over long horizons. This capability, however, introduces novel safety risks, as responses that are generally safe may become harmful in user-specific contexts. Such safety-relevant contexts often emerge implicitly...
Zhou Feng · Jiahao Chen · Chunyi Zhou · Yuwen Pu · Tianyu Du · Jinbao Li · Jianhai Chen · Shouling Ji