collaborators

5 papers

cs.AI2026

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…

cs.AI2026

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…

cs.CV2025

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…

cs.CL2025

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…

cs.CV2025

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…