11 papers
When Words Are Safe But Actions Kill: Probing Physical Jailbreak Beyond Textual Jailbreak in Hidden-State Risk Space
Weimeng Wang, Ziqiang Wang, Zihang Zhan +3
Large language models (LLMs) increasingly serve as high-level planners for embodied agents, where linguistically benign instructions can become unsafe once grounded in the physical…
AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents
Yixiang Zhang, Xinhao Deng, Jiaqing Wu +3
Autonomous AI agents extend large language models into full runtime systems that load skills, ingest external content, maintain memory, plan multi-step actions, and invoke privileg…
Chain-of-Authorization: Embedding authorization into large language models
Yang Li, Yule Liu, Xinlei He +3
Although Large Language Models (LLMs) have evolved from text generators into the cognitive core of modern AI systems, their inherent lack of authorization awareness exposes these s…
Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
Qi Li, Bo Yin, Weiqi Huang +6
Vision-Language-Action (VLA) models are emerging as a unified substrate for embodied intelligence. This shift raises a new class of safety challenges, stemming from the embodied na…
How Far Should We Need to Go : Evaluate Provenance-based Intrusion Detection Systems in Industrial Scenarios
Yue Xiao, Ling Jiang, Sen Nie +4
Provenance-based Intrusion Detection Systems (PIDSes) have been widely used to detect Advanced Persistent Threats (APTs). Although many studies achieve high performance in the eval…
LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning
Jianing Wang, Jianfei Zhang, Qi Guo +24
We introduce LongCat-Flash-Prover, a flagship 560-billion-parameter open-source Mixture-of- Experts (MoE) model that advances Native Formal Reasoning in Lean4 through agentic tool-…
Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats
Xinhao Deng, Yixiang Zhang, Jiaqing Wu +15
Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled…
Automating Agent Hijacking via Structural Template Injection
Xinhao Deng, Jiaqing Wu, Miao Chen +3
Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate execution by injecting malicious instructi…
A Hard-Label Black-Box Evasion Attack against ML-based Malicious Traffic Detection Systems
Zixuan Liu, Yi Zhao, Zhuotao Liu +4
Machine Learning (ML)-based malicious traffic detection is a promising security paradigm. It outperforms rule-based traditional detection by identifying various advanced attacks. H…
Beyond a Single Perspective: Towards a Realistic Evaluation of Website Fingerprinting Attacks
Xinhao Deng, Jingyou Chen, Linxiao Yu +6
Website Fingerprinting (WF) attacks exploit patterns in encrypted traffic to infer the websites visited by users, posing a serious threat to anonymous communication systems. Althou…
Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions
Yixiang Zhang, Xinhao Deng, Zhongyi Gu +4
Large Language Models (LLMs) are increasingly deployed as agents that orchestrate tasks and integrate external tools to execute complex workflows. We demonstrate that these interac…