5 papers
JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety
Yuan Xiong, Linji Hao, Shizhu He +2
Agent safety is moving from content moderation toward preventing operational failures before tool-using agents act. We propose Janus, a foresight-oriented framework for long-horizo…
SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring
Chunxiao Li, Yuan Xiong, Lijun Li +4
Large language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance. Existing benchmarks often rely…
Contextual Image Attack: How Visual Context Exposes Multimodal Safety Vulnerabilities
Yuan Xiong, Ziqi Miao, Lijun Li +3
While Multimodal Large Language Models (MLLMs) show remarkable capabilities, their safety alignments are susceptible to jailbreak attacks. Existing attack methods typically focus o…
Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models
Ziqi Miao, Lijun Li, Yuan Xiong +3
Contextual priming, where earlier stimuli covertly bias later judgments, offers an unexplored attack surface for large language models (LLMs). We uncover a contextual priming vulne…
IAD-R1: Reinforcing Consistent Reasoning in Industrial Anomaly Detection
Yanhui Li, Yunkang Cao, Chengliang Liu +3
Industrial anomaly detection is a critical component of modern manufacturing, yet the scarcity of defective samples restricts traditional detection methods to scenario-specific app…