会员服务
Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw
Arxiv
0+阅读 · 6月14日
Security Engineering of OpenClaw: Analyzing Attack Surface Expansion and Trust-Boundary Violations
Arxiv
0+阅读 · 6月12日
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
Arxiv
0+阅读 · 5月11日
Understanding and mitigating the risks of OpenClaw for non-technical users: A practical guide with Skill
Arxiv
0+阅读 · 6月9日
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
Arxiv
0+阅读 · 6月10日
Security, Privacy, and Ethical Risks in OpenClaw
Arxiv
0+阅读 · 5月22日
RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions
Arxiv
0+阅读 · 6月2日
MATRA: Modeling the Attack Surface of Agentic AI Systems -- OpenClaw Case Study
Arxiv
0+阅读 · 5月11日
ClawTrap: A MITM-Based Red-Teaming Framework for Real-World OpenClaw Security Evaluation
Arxiv
0+阅读 · 3月19日
Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped Guidance
Arxiv
0+阅读 · 3月20日
AcademiClaw: When Students Set Challenges for AI Agents
Arxiv
0+阅读 · 5月4日
Foundations for Agentic AI Investigations from the Forensic Analysis of OpenClaw
Arxiv
0+阅读 · 4月7日
A Systematic Security Evaluation of OpenClaw and Its Variants
Arxiv
0+阅读 · 4月3日
Autonomous Agent-Orchestrated Digital Twins (AADT): Leveraging the OpenClaw Framework for State Synchronization in Rare Genetic Disorders
Arxiv
0+阅读 · 3月28日
Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
Arxiv
0+阅读 · 4月6日
参考链接
微信扫码咨询专知VIP会员
Top