中文
相关论文

相关论文: A Trajectory-Based Safety Audit of Clawdbot (OpenC…

200 篇论文

Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond…

人工智能 · 计算机科学 2026-04-07 Bowen Wei , Yunbei Zhang , Jinhao Pan , Kai Mei , Xiao Wang , Jihun Hamm , Ziwei Zhu , Yingqiang Ge

Autonomous AI agents deployed on platforms such as OpenClaw face prompt injection, memory poisoning, supply-chain attacks, and social engineering, yet existing defences address only the platform perimeter, leaving the agent's own threat…

密码学与安全 · 计算机科学 2026-04-28 Jiaqi Li , Yang Zhao , Bin Sun , Yang Yu , Jian Chang , Lidong Zhai

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…

人工智能 · 计算机科学 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

Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they also introduce security risks that cannot be identified through model-only evaluation. In this paper, we present a systematic…

密码学与安全 · 计算机科学 2026-04-06 Yuhang Wang , Haichang Gao , Zhenxing Niu , Zhaoxiang Liu , Wenjing Zhang , Xiang Wang , Shiguo Lian

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…

人工智能 · 计算机科学 2026-05-19 Ashwin Aravind

Large language model (LLM) agents are increasingly deployed to automate productivity tasks (e.g., email, scheduling, document management), but evaluating them on live services is risky due to potentially irreversible changes. Existing…

Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, safety-critical environments. As these systems gain autonomy and enter domains such as…

As agent systems move into increasingly diverse execution settings, trajectory-level safety evaluation and diagnosis require benchmarks that evolve with them. ATBench is a diverse and realistic agent trajectory benchmark for safety…

人工智能 · 计算机科学 2026-04-30 Zhonghao Yang , Yu Li , Yanxu Zhu , Tianyi Zhou , Yuejin Xie , Haoyu Luo , Jing Shao , Xia Hu , Dongrui Liu

This paper systematically investigates the security, privacy, and ethical risks, as well as the traceability challenges of OpenClaw, a locally executable AI agent system for natural language interaction and real-world task completion. While…

密码学与安全 · 计算机科学 2026-05-25 Yutong Jin , Zelin Zhang , Zhijin Lyu , Jianbing Ni

Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than isolated prompts or final responses. Existing trajectory-level benchmarks…

人工智能 · 计算机科学 2026-05-14 Yu Li , Haoyu Luo , Yuejin Xie , Yuqian Fu , Zhonghao Yang , Shuai Shao , Qihan Ren , Wanying Qu , Yanwei Fu , Yujiu Yang , Jing Shao , Xia Hu , Dongrui Liu

Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…

Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While…

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…

密码学与安全 · 计算机科学 2026-03-30 Shiping Chen , Qin Wang , Guangsheng Yu , Xu Wang , Liming Zhu

The rise of AI agents introduces complex safety and security challenges arising from autonomous tool use and environmental interactions. Current guardrail models lack agentic risk awareness and transparency in risk diagnosis. To introduce…

Personalized computer-use agents are rapidly moving from expert communities into mainstream use. Unlike conventional chatbots, these systems can install skills, invoke tools, access private resources, and modify local environments on users'…

密码学与安全 · 计算机科学 2026-04-01 Zifan Peng , Mingchen Li

The rapid evolution of Large Language Models (LLMs) into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Frameworks like OpenClaw grant AI systems operating-system-level permissions and the autonomy to…

密码学与安全 · 计算机科学 2026-03-16 Zonghao Ying , Xiao Yang , Siyang Wu , Yumeng Song , Yang Qu , Hainan Li , Tianlin Li , Jiakai Wang , Aishan Liu , Xianglong Liu

AI agent frameworks connecting large language model (LLM) reasoning to host execution surfaces -- shell, filesystem, containers, and messaging -- introduce security challenges structurally distinct from conventional software. We present a…

密码学与安全 · 计算机科学 2026-05-15 Surada Suwansathit , Yuxuan Zhang , Guofei Gu

In January 2026, the open-source agent framework OpenClaw and the agent-only social network Moltbook produced a large-scale dataset of autonomous AI-to-AI interaction, attracting six academic publications within fourteen days. This study…

人工智能 · 计算机科学 2026-03-05 Lukas Weidener , Marko Brkić , Phillip Lee , Martin Karlsson , Kevin Noessler , Paul Kohlhaas

Embodied AI research is increasingly moving beyond single-task, single-environment policy learning toward multi-task, multi-scene, and multi-model settings. This shift substantially increases the engineering overhead and development time…

机器人学 · 计算机科学 2026-04-16 Xueyang Zhou , Yihan Sun , Xijie Gong , Guiyao Tie , Pan Zhou , Lichao Sun , Yongchao Chen

Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege…

‹ 上一页 1 2 3 10 下一页 ›