7 papers · 1 filter
An Early Warning of Emerging Biosecurity Risks in Frontier LLMs
Zhida He, Xia Hu, Baichen Le +20
Frontier large language models (LLMs) are increasingly integrated into scientific workflows, yet their growing biological capabilities may outpace current safeguards. To assess the…
Evolutionary Guided Decoding: Iterative Value Refinement for LLMs
Zhenhua Liu, Lijun Li, Ruizhe Chen +5
While guided decoding, especially value-guided methods, has emerged as a cost-effective alternative for controlling language model outputs without re-training models, its effective…
ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
Yutao Mou, Zhangchi Xue, Lijun Li +4
While LLM-based agents can interact with environments via invoking external tools, their expanded capabilities also amplify security risks. Monitoring step-level tool invocation be…
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…
T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation
Lijun Li, Zhelun Shi, Xuhao Hu +5
Text-to-image (T2I) models have rapidly advanced, enabling the generation of high-quality images from text prompts across various domains. However, these models present notable saf…
PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety
Zaibin Zhang, Yongting Zhang, Lijun Li +6
Multi-agent systems, when enhanced with Large Language Models (LLMs), exhibit profound capabilities in collective intelligence. However, the potential misuse of this intelligence f…