11 papers
Self-Reflection Fine-Tuning: Enhancing Agent Security against Prompt Injection Attacks from Failure Experience
Zixuan Wang, Hao Li, Fengyu Gao +5
Large language model (LLM) agents are increasingly deployed in tool-augmented environments, but their reliance on external inputs makes them highly vulnerable to prompt injection a…
Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety
Ping Wu, Haibo Tong, Feifei Zhao +7
A common way to improve jailbreak robustness is to train on harmful requests rewritten as role-play, translation, or other forms. When used only for harmful requests, these forms m…
When Truth Is Distributed: Misinformation Derails Collective Fact Recovery in LLM-Based Multi-Agent Systems
Chenfei Yan, Zeyang Yue, Feifei Zhao +6
LLM-based multi-agent systems promise effective collaborative reasoning, but communication may amplify local errors into collective risks, and while existing evaluations emphasize…
ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models
Mingyang Lyu, Yinqian Sun, Yiyang Jia +5
In embodied intelligence, safety is a prerequisite for reliable robot deployment in the physical world. Current vision-language-action (VLA) models continue to advance toward gener…
SciRisk-Bench: A Risk-Dimension-Aware Benchmark for AI4Science Safety
Linghao Feng, Yinqian Sun, Dongqi Liang +8
Large language models (LLMs) are increasingly embedded in AI for Science (AI4Science) workflows, from scientific question answering and literature analysis to laboratory planning a…
ForesightSafety-SAGE:A Fully Automated Scenario Generation and Safety Evaluation Framework for LLM Agents
Lu Jia, Haibo Tong, Feifei Zhao +5
Large language models (LLMs) are increasingly evolving from simple text-based interaction systems into LLM agents that can maintain memory, use tools, access external environments,…
ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI
Haibo Tong, Feifei Zhao, Linghao Feng +18
Rapidly evolving AI exhibits increasingly strong autonomy and goal-directed capabilities, accompanied by derivative systemic risks that are more unpredictable, difficult to control…
CogToM: A Comprehensive Theory of Mind Benchmark inspired by Human Cognition for Large Language Models
Haibo Tong, Zeyang Yue, Feifei Zhao +6
Whether Large Language Models (LLMs) truly possess human-like Theory of Mind (ToM) capabilities has garnered increasing attention. However, existing benchmarks remain largely restr…
Towards Reliable Evaluation of Adversarial Robustness for Spiking Neural Networks
Jihang Wang, Dongcheng Zhao, Ruolin Chen +2
Spiking Neural Networks (SNNs) utilize spike-based activations to mimic the brain's energy-efficient information processing. However, the binary and discontinuous nature of spike a…
Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models
Mingyang Lyu, Yinqian Sun, Erliang Lin +4
Vision-Language-Action (VLA) models such as OpenVLA, Octo, and have shown strong generalization by leveraging large-scale demonstrations, yet their performance is still funda…
SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM Agents
Ruolin Chen, Yinqian Sun, Jihang Wang +3
Embodied agents powered by large language models (LLMs) inherit advanced planning capabilities; however, their direct interaction with the physical world exposes them to safety vul…