10 papers
TRAP: Tool-result Replay Attack for Probing Misbinding in LLM Agents
Yutong Zhi, Jie Zhang, Xiuqi Lu +2
As AI agents increasingly act through external tools, tool results are no longer simple outputs but execution artifacts that must remain correctly associated with the context that…
DRYLAB-Bench: Benchmarking the Biosecurity Risk of Agentic LLM Mutation Design
Yuzhen Wang, Chunxiao Li, Baichen Le +6
As large language models (LLMs) acquire advanced biological design capabilities, they offer substantial research benefits but simultaneously introduce severe dual-use risks, such a…
Imprint Reader: From Weight-Update Readout to Behavioral Intervention
Guanxu Chen, Qihao Lin, Jing Shao
As language models take a growing role in AI development, a natural aspiration is for them to reflect on their own learning process, as humans do, and use that reflection to improv…
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…
READER: Dynamic LLM Provenance from Query-Varying Interactions
Jiaxu Liu, Sunnan Mu, Dong Huang +3
Existing black-box LLM provenance methods achieve comparability by querying every candidate model with the same diagnostic prompts. In deployment, auditors inherit a different evid…
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond
Xiangyang Zhu, Yuan Tian, Qi Jia +14
The success of large language models (LLMs) in scientific domains has heightened safety concerns, prompting numerous benchmarks to evaluate their scientific safety. Existing benchm…
Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5
Dongrui Liu, Yi Yu, Jie Zhang +18
To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comp…
DeepSight: An All-in-One LM Safety Toolkit
Bo Zhang, Jiaxuan Guo, Lijun Li +17
As the development of Large Models (LMs) progresses rapidly, their safety is also a priority. In current Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) s…
LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions
Xuhao Hu, Peng Wang, Xiaoya Lu +3
Previous research has shown that LLMs finetuned on malicious or incorrect completions within narrow domains (e.g., insecure code or incorrect medical advice) can become broadly mis…
Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Step
Jingyi Yang, Guanxu Chen, Xuhao Hu +1
Masked diffusion language models (MDLMs) have recently emerged as a promising alternative to autoregressive (AR) language models, offering properties such as parallel decoding, fle…