English
Related papers

Related papers: AgentHazard: A Benchmark for Evaluating Harmful Be…

200 papers

Third-party skills are becoming the package ecosystem for LLM agents. They package natural-language instructions, helper scripts, templates, documents, and service configuration into reusable workflows. This makes skills useful, but it also…

Cryptography and Security · Computer Science 2026-05-15 Haomin Zhuang , Hanwen Xing , Yujun Zhou , Yuchen Ma , Yue Huang , Yili Shen , Yufei Han , Xiangliang Zhang

LLM-based agents are becoming increasingly proficient at solving web-based tasks. With this capability comes a greater risk of misuse for malicious purposes, such as posting misinformation in an online forum or selling illicit substances on…

Multi-agent systems coordinate LLM-based agents to perform tasks on users' behalf. In real-world applications, multi-agent systems will inevitably interact with untrusted inputs, such as malicious Web content, files, email attachments, and…

Cryptography and Security · Computer Science 2025-09-16 Harold Triedman , Rishi Jha , Vitaly Shmatikov

Computer Use Agents (CUAs), autonomous systems that interact with software interfaces via browsers or virtual machines, are rapidly being deployed in consumer and enterprise environments. These agents introduce novel attack surfaces and…

Personalized LLM agents maintain persistent cross-session state to support long-horizon collaboration. Yet, this persistence introduces a subtle but critical security vulnerability: routine user-agent interactions can gradually reshape an…

Cryptography and Security · Computer Science 2026-05-11 Xiaoyu Xu , Minxin Du , Qipeng Xie , Haobin Ke , Qingqing Ye , Haibo Hu

Computer-use agent (CUA) frameworks, powered by large language models (LLMs) or multimodal LLMs (MLLMs), are rapidly maturing as assistants that can perceive context, reason, and act directly within software environments. Among their most…

Cryptography and Security · Computer Science 2025-10-13 Weidi Luo , Qiming Zhang , Tianyu Lu , Xiaogeng Liu , Bin Hu , Hung-Chun Chiu , Siyuan Ma , Yizhe Zhang , Xusheng Xiao , Yinzhi Cao , Zhen Xiang , Chaowei Xiao

Although computer-use agents (CUAs) hold significant potential to automate increasingly complex OS workflows, they can demonstrate unsafe unintended behaviors that deviate from expected outcomes even under benign input contexts. However,…

Computation and Language · Computer Science 2026-02-10 Jaylen Jones , Zhehao Zhang , Yuting Ning , Eric Fosler-Lussier , Pierre-Luc St-Charles , Yoshua Bengio , Dawn Song , Yu Su , Huan Sun

Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However, most agent benchmarks still rely on synthetic sandboxes, short-horizon tasks,…

Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this…

Cryptography and Security · Computer Science 2026-03-30 Shiping Chen , Qin Wang , Guangsheng Yu , Xu Wang , Liming Zhu

With the integration of large language models (LLMs), embodied agents have strong capabilities to understand and plan complicated natural language instructions. However, a foreseeable issue is that those embodied agents can also flawlessly…

Cryptography and Security · Computer Science 2025-11-03 Sheng Yin , Xianghe Pang , Yuanzhuo Ding , Menglan Chen , Yutong Bi , Yichen Xiong , Wenhao Huang , Zhen Xiang , Jing Shao , Siheng Chen

With the rapid development of multimodal large language models (MLLMs), they are increasingly deployed as autonomous computer-use agents capable of accomplishing complex computer tasks. However, a pressing issue arises: Can the safety risk…

Artificial Intelligence · Computer Science 2025-06-23 Jingyi Yang , Shuai Shao , Dongrui Liu , Jing Shao

The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, where an adversary induces an agent to execute dangerous…

Cryptography and Security · Computer Science 2026-05-12 Chiyu Zhang , Huiqin Yang , Bendong Jiang , Xiaolei Zhang , Yiran Zhao , Ruyi Chen , Lu Zhou , Xiaogang Xu , Jiafei Wu , Liming Fang , Zhe Liu

Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems in AI safety: understanding dangerous internal computations, removing dangerous behaviors…

Machine Learning · Computer Science 2026-04-02 Aengus Lynch

Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents through tool use, planning, and decision-making abilities, leading to their widespread adoption across diverse tasks. As task complexity grows,…

Multiagent Systems · Computer Science 2025-11-10 Ishan Kavathekar , Hemang Jain , Ameya Rathod , Ponnurangam Kumaraguru , Tanuja Ganu

With the wide application of multimodal foundation models in intelligent agent systems, scenarios such as mobile device control, intelligent assistant interaction, and multimodal task execution are gradually relying on such large…

Artificial Intelligence · Computer Science 2025-07-02 Siyuan Liang , Tianmeng Fang , Zhe Liu , Aishan Liu , Yan Xiao , Jinyuan He , Ee-Chien Chang , Xiaochun Cao

Random rules improve a coding agent's task performance as much as expert-curated ones (both $+13.8$pp on a discriminative subset of SWE-bench Verified), and in our data every individually beneficial rule is a negative constraint ("do not…

Artificial Intelligence · Computer Science 2026-05-29 Xing Zhang , Guanghui Wang , Yanwei Cui , Wei Qiu , Ziyuan Li , Bing Zhu , Peiyang He

The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active actors capable of executing shell commands, modifying files, calling APIs, and browsing…

Artificial Intelligence · Computer Science 2026-05-19 Ashwin Aravind

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

Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over long-lasting tasks. By integrating memory, tool use, and iterative decision cycles, these…

Cryptography and Security · Computer Science 2026-01-12 Sahaya Jestus Lazer , Kshitiz Aryal , Maanak Gupta , Elisa Bertino

Tool-using language agents turn model decisions into external side effects: they read files, run scripts, call APIs, send messages, and invoke Model Context Protocol tools. This makes agent attacks different from jailbreaks. The harmful…

Cryptography and Security · Computer Science 2026-05-29 Suliu Qin , Haomin Zhuang , Yujun Zhou , Yufei Han , Xiangliang Zhang