Copertina

From Assistant to Double Agent: Formalizing and Benchmarking Attacks on OpenClaw for Personalized Local AI Agent

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Yuhang, Xu, Feiming, Lin, Zheng, He, Guangyu, Huang, Yuzhe, Gao, Haichang, Niu, Zhenxing, Lian, Shiguo, Liu, Zhaoxiang
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

A Systematic Security Evaluation of OpenClaw and Its Variants
di: Wang, Yuhang, et al.
Pubblicazione: (2026)

A Security Analysis of the OpenClaw AI Agent Framework
di: Suwansathit, Surada, et al.
Pubblicazione: (2026)

OpenClaw-RL: Train Any Agent Simply by Talking
di: Wang, Yinjie, et al.
Pubblicazione: (2026)

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers
di: Liu, Songyang, et al.
Pubblicazione: (2026)

ICU-Bench:Benchmarking Continual Unlearning in Multimodal Large Language Models
di: Wang, Yuhang, et al.
Pubblicazione: (2026)

Defensible Design for OpenClaw: Securing Autonomous Tool-Invoking Agents
di: Li, Zongwei, et al.
Pubblicazione: (2026)

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
di: Wang, Zijun, et al.
Pubblicazione: (2026)

QuantClaw: Precision Where It Matters for OpenClaw
di: Zhang, Manyi, et al.
Pubblicazione: (2026)

OpenClaw AI Agents as Informal Learners at Moltbook: Characterizing an Emergent Learning Community at Scale
di: Chen, Eason, et al.
Pubblicazione: (2026)

Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw
di: Yao, Hongwei, et al.
Pubblicazione: (2026)

Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats
di: Deng, Xinhao, et al.
Pubblicazione: (2026)

MATRA: Modeling the Attack Surface of Agentic AI Systems -- OpenClaw Case Study
di: Van hamme, Tim, et al.
Pubblicazione: (2026)

Attention-Guided Reward for Reinforcement Learning-based Jailbreak against Large Reasoning Models
di: Lin, Zheng, et al.
Pubblicazione: (2026)

Re-Triggering Safeguards within LLMs for Jailbreak Detection
di: Lin, Zheng, et al.
Pubblicazione: (2026)

OpenClaw Agents on Moltbook: Risky Instruction Sharing and Norm Enforcement in an Agent-Only Social Network
di: Manik, Md Motaleb Hossen, et al.
Pubblicazione: (2026)

Agent Privilege Separation in OpenClaw: A Structural Defense Against Prompt Injection
di: Cheng, Darren, et al.
Pubblicazione: (2026)

Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents
di: Dong, Ben, et al.
Pubblicazione: (2026)

Benchmarks for Trajectory Safety Evaluation and Diagnosis in OpenClaw and Codex: ATBench-Claw and ATBench-Codex
di: Yang, Zhonghao, et al.
Pubblicazione: (2026)

Security Attack and Defense Strategies for Autonomous Agent Frameworks: A Layered Review with OpenClaw as a Case Study
di: Xu, Luyao, et al.
Pubblicazione: (2026)

Security, Privacy, and Ethical Risks in OpenClaw
di: Jin, Yutong, et al.
Pubblicazione: (2026)

Null Space Constrained Contrastive Visual Forgetting for MLLM Unlearning
di: Wang, Yuhang, et al.
Pubblicazione: (2026)

Robust MLLM Unlearning via Visual Knowledge Distillation
di: Wang, Yuhang, et al.
Pubblicazione: (2025)

Foundations for Agentic AI Investigations from the Forensic Analysis of OpenClaw
di: Gruber, Jan, et al.
Pubblicazione: (2026)

Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw
di: Ying, Zonghao, et al.
Pubblicazione: (2026)

When AI Agents Learn from Each Other: Insights from Emergent AI Agent Communities on OpenClaw for Human-AI Partnership in Education
di: Chen, Eason, et al.
Pubblicazione: (2026)

GlitchMiner: Mining Glitch Tokens in Large Language Models via Gradient-based Discrete Optimization
di: Wu, Zihui, et al.
Pubblicazione: (2024)

Execution Is the New Attack Surface: Survivability-Aware Agentic Crypto Trading with OpenClaw-Style Local Executors
di: Borjigin, Ailiya, et al.
Pubblicazione: (2026)

A Trajectory-Based Safety Audit of Clawdbot (OpenClaw)
di: Chen, Tianyu, et al.
Pubblicazione: (2026)

Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
di: Lin, Zheng, et al.
Pubblicazione: (2026)

Autonomous Agent-Orchestrated Digital Twins (AADT): Leveraging the OpenClaw Framework for State Synchronization in Rare Genetic Disorders
di: Chen, Hongzhuo, et al.
Pubblicazione: (2026)

OpenClaw PRISM: A Zero-Fork, Defense-in-Depth Runtime Security Layer for Tool-Augmented LLM Agents
di: Li, Frank
Pubblicazione: (2026)

Don't Let the Claw Grip Your Hand: A Security Analysis and Defense Framework for OpenClaw
di: Shan, Zhengyang, et al.
Pubblicazione: (2026)

From Agent-Only Social Networks to Autonomous Scientific Research: Lessons from OpenClaw and Moltbook, and the Architecture of ClawdLab and Beach.Science
di: Weidener, Lukas, et al.
Pubblicazione: (2026)

SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants
di: Wang, Haoyu, et al.
Pubblicazione: (2026)

OpenGo: An OpenClaw-Based Robotic Dog with Real-Time Skill Switching
di: Li, Hanbing, et al.
Pubblicazione: (2026)

ClawTrap: A MITM-Based Red-Teaming Framework for Real-World OpenClaw Security Evaluation
di: Zhao, Haochen, et al.
Pubblicazione: (2026)

MediaClaw: Multimodal Intelligent-Agent Platform Technical Report
di: Zhao, Shaoan, et al.
Pubblicazione: (2026)

Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped Guidance
di: Liu, Fazhong, et al.
Pubblicazione: (2026)

Automating Computational Chemistry Workflows via OpenClaw and Domain-Specific Skills
di: Ding, Mingwei, et al.
Pubblicazione: (2026)

ROSClaw: An OpenClaw ROS 2 Framework for Agentic Robot Control and Interaction
di: Cardenas, Irvin Steve, et al.
Pubblicazione: (2026)