English
Related papers

Related papers: StepShield: When, Not Whether to Intervene on Rogu…

200 papers

Autonomous agents have rapidly matured as task executors and seen widespread deployment via harnesses such as OpenClaw. Safety concerns have rightly drawn growing research attention, and beneath them lie the values silently steering agent…

Artificial Intelligence · Computer Science 2026-05-12 Haonan Dong , Qiguan Feng , Kehan Jiang , Haoran Ye , Xin Zhang , Guojie Song

Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…

Modern threat landscapes continue to evolve with increasing sophistication, challenging traditional detection methodologies and necessitating innovative solutions capable of addressing complex adversarial tactics. A novel framework was…

Cryptography and Security · Computer Science 2025-03-27 Levi Gareth , Maximilian Fairbrother , Peregrine Blackwood , Lucasta Underhill , Benedict Ruthermore

Large Language Models (LLMs) exhibit substantial promise in enhancing task-planning capabilities within embodied agents due to their advanced reasoning and comprehension. However, the systemic safety of these agents remains an underexplored…

Artificial Intelligence · Computer Science 2025-04-22 Yuting Huang , Leilei Ding , Zhipeng Tang , Tianfu Wang , Xinrui Lin , Wuyang Zhang , Mingxiao Ma , Yanyong Zhang

AI systems have become increasingly capable of dangerous behaviours in many domains. This raises the question: Do models sometimes choose to violate human instructions in order to perform behaviour that is more useful for certain goals? We…

Artificial Intelligence · Computer Science 2026-05-08 Jonas Wiedermann-Möller , Leonard Dung , Maksym Andriushchenko

The rapid advancement of large language model (LLM) agents has raised new concerns regarding their safety and security. In this paper, we propose GuardAgent, the first guardrail agent to protect target agents by dynamically checking whether…

Machine Learning · Computer Science 2025-05-30 Zhen Xiang , Linzhi Zheng , Yanjie Li , Junyuan Hong , Qinbin Li , Han Xie , Jiawei Zhang , Zidi Xiong , Chulin Xie , Carl Yang , Dawn Song , Bo Li

Recent advances in frontier large language models have enabled code review agents that operate in open-ended, reasoning-intensive settings. However, the lack of standardized benchmarks and granular evaluation protocols makes it difficult to…

Software Engineering · Computer Science 2026-03-13 Kristen Pereira , Neelabh Sinha , Rajat Ghosh , Debojyoti Dutta

Safety risks arise as large language model-based agents solve complex tasks with tools, multi-step plans, and inter-agent messages. However, deployer-written policies in natural language are ambiguous and context dependent, so they map…

Artificial Intelligence · Computer Science 2025-12-19 Yiliu Yang , Yilei Jiang , Qunzhong Wang , Yingshui Tan , Xiaoyong Zhu , Sherman S. M. Chow , Bo Zheng , Xiangyu Yue

We evaluate the autonomous cyber-attack capabilities of frontier AI models on two purpose-built cyber ranges-a 32-step corporate network attack and a 7-step industrial control system attack-that require chaining heterogeneous capabilities…

Large language models are increasingly deployed as autonomous agents for multi-step workflows in real-world software environments. However, existing agent benchmarks are limited by trajectory-opaque grading, underspecified safety and…

Artificial Intelligence · Computer Science 2026-05-08 Bowen Ye , Rang Li , Qibin Yang , Yuanxin Liu , Linli Yao , Hanglong Lv , Zhihui Xie , Chenxin An , Lei Li , Lingpeng Kong , Qi Liu , Zhifang Sui , Tong Yang

Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hacking, where agents maximize a score without performing the intended task, emerges…

Artificial Intelligence · Computer Science 2026-05-14 Hao Wang , Hanchen Li , Qiuyang Mang , Alvin Cheung , Koushik Sen , Dawn Song

AI agents often fail in ways that are difficult to localize because executions are probabilistic, long-horizon, multi-agent, and mediated by noisy tool outputs. We address this gap by manually annotating failed agent runs and release a…

Artificial Intelligence · Computer Science 2026-02-03 Shraddha Barke , Arnav Goyal , Alind Khare , Avaljot Singh , Suman Nath , Chetan Bansal

Embodied agents exhibit immense potential across a multitude of domains, making the assurance of their behavioral safety a fundamental prerequisite for their widespread deployment. However, existing research predominantly concentrates on…

Artificial Intelligence · Computer Science 2025-06-23 Ning Wang , Zihan Yan , Weiyang Li , Chuan Ma , He Chen , Tao Xiang

Large language models (LLMs) have evolved into autonomous agents that rely on open skill ecosystems (e.g., ClawHub and Skills.Rest), hosting numerous publicly reusable skills. Existing security research on these ecosystems mainly focuses on…

Cryptography and Security · Computer Science 2026-04-20 Yukun Jiang , Yage Zhang , Michael Backes , Xinyue Shen , Yang Zhang

As large language models (LLMs) become high-privilege agents in risk-sensitive settings, they introduce systemic threats beyond hallucination, where minor compliance errors can cause critical data leaks. However, existing benchmarks focus…

Computational Engineering, Finance, and Science · Computer Science 2026-02-16 Jinru Ding , Chao Ding , Yidong Jiang , Wenrao Pang , Boyi Xiao , Zhiqiang Liu , Jiayuan Chen , Yun Zhong , Tiantian Yuan , Junming Guan , Dawei Cheng , Jie Xu

Large language model agents increasingly operate through environment-facing scaffolds that expose files, web pages, APIs, and logs. These observations influence tool use, state tracking, and action sequencing, yet their reliability and…

Artificial Intelligence · Computer Science 2026-05-13 Strick Sheng , Ziyue Wang , Liyi Zhou

Cybersecurity spans multiple interconnected domains, complicating the development of meaningful, labor-relevant benchmarks. Existing benchmarks assess isolated skills rather than integrated performance. We find that pre-trained knowledge of…

Anomaly detection (AD) has garnered ample attention in security research, as such algorithms complement existing signature-based methods but promise detection of never-before-seen attacks. Cyber operations manage a high volume of…

Cryptography and Security · Computer Science 2017-10-27 Robert A. Bridges , Jessie D. Jamieson , Joel W. Reed

Cyber-Physical Systems (CPS) play a significant role in our critical infrastructure networks from power-distribution to utility networks. The emerging smart-grid concept is a compelling critical CPS infrastructure that relies on two-way…

Cryptography and Security · Computer Science 2019-12-03 Leonardo Babun , Hidayet Aksu , A. Selcuk Uluagac