ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

~ similar to 2606.01166v2· 20 results

cs.CRcs.CLRecentMay 31, 2026

BraveGuard: From Open-World Threats to Safer Computer-Use Agents

Yunhao Feng, Yifan Ding, Xiaohu Du, Ming Wen +12 more

BraveGuard is a self-evolving defense framework that improves the safety of computer-use agents by training guard models on open-world, multi-step threat trajectories rather than static benchmarks.

View →
cs.CRcs.AIcs.CLMay 4, 2026

MAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory

Yuhui Wang, Tanqiu Jiang, Jiacheng Liang, Charles Fleming +1 more

The paper introduces MAGE, a novel defensive framework that uses a dedicated 'shadow memory' to proactively detect and mitigate long-horizon threats against LLM agents during complex, multi-step inter…

View →
cs.CRcs.AIcs.CLMay 12, 2026

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces

Chang Jin, An Wang, Zeming Wei, Kai Wang +6 more

The paper introduces SkillSafetyBench, a comprehensive benchmark demonstrating that agent safety failures often stem from adversarial influences within reusable skills and execution environments, rath…

View →
cs.CLRecentMay 29, 2026

EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents

Dongwook Choi, Taeyoon Kwon, Bogyung Jeong, Minju Kim +5 more

EMBGuard introduces a novel, MLLM-based safety guardrail that explicitly identifies and explains physical hazards from (visual observation, action) pairs, enabling safer planning for embodied agents.

View →
cs.CRApr 14, 2026

WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents

Yulin Chen, Tri Cao, Haoran Li, Yue Liu +6 more

The paper introduces WebAgentGuard, a novel reasoning-driven, multimodal guard model that effectively detects prompt injection attacks in vulnerable web agents without compromising their functionality…

View →
cs.CRcs.AIcs.CLEmpiricalRecentOct 20, 2026

MAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems

Mohammad Kachuee, Phu Mon Htut, Sheng Li, Nikolaos Pappas +4 more

The paper introduces MAS-Guard, a unified framework for safeguarding single- and multi-agent AI applications against threats such as unsafe actions and information leakage.

View →
cs.CRMar 28, 2026

SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants

Haoyu Wang, Zibo Xiao, Yedi Zhang, Christopher M. Poskitt +1 more

The paper proposes SafeClaw-R, a novel framework that enforces safety as a system-level invariant over the execution graph to mitigate the high safety and security risks inherent in autonomous multi-a…

View →
cs.CRcs.AIcs.CLRecentJun 3, 2026

Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming

Nicholas Saban

The paper benchmarks current frontier computer-using agents against hand-crafted attacks, finding that while they are highly safe in browser tasks, this safety does not generalize to other domains lik…

View →
cs.CRcs.CLRecentMay 29, 2026

Triaging Threats to Specialized Guardrails

Wenjie Jacky Mo, Xiaofei Wen, Rui Cai, Boyu Zhu +5 more

The paper introduces RouteGuard, a router-expert framework, to improve the robustness and generalization of safety guardrails by specializing threat detection across multiple unsafe categories.

View →
cs.CRcs.CLRecentMay 29, 2026

Triaging Threats to Specialized Guardrails

Wenjie Jacky Mo, Xiaofei Wen, Rui Cai, Boyu Zhu +5 more

The paper introduces RouteGuard, a router-expert framework, to improve the robustness and generalization of safety guardrails by specializing threat detection across multiple distinct unsafe categorie…

View →
cs.CRcs.AIMay 11, 2026

Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw

Hongwei Yao, Yiming Liu, Yiling He, Bingrun Yang

The paper introduces DeepTrap, an automated framework that evaluates security vulnerabilities in agentic language models by manipulating their internal execution contexts, demonstrating that task comp…

View →
cs.CRcs.AIcs.SEEmpiricalRecentJun 9, 2026

Understanding and mitigating the risks of OpenClaw for non-technical users: A practical guide with Skill

Junchang Zheng, Junfeng Tan, Jialiang Lin

The paper identifies and categorizes risks associated with OpenClaw AI agent framework and provides practical guidance for non-technical users to mitigate these risks.

View →
cs.CRcs.AIApr 14, 2026

Parallax: Why AI Agents That Think Must Never Act

Joel Fokou

The paper introduces Parallax, an architectural framework that structurally separates AI reasoning from action execution to ensure robust safety for autonomous agents, achieving high attack mitigation…

View →
cs.CRcs.AIcs.CLApr 8, 2026

TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang, Yun-Nung Chen

The paper introduces TraceSafe-Bench, a comprehensive benchmark, and finds that securing LLM agents requires jointly optimizing for structural reasoning and safety alignment to mitigate risks during m…

View →
cs.CRcs.AIcs.CLApr 20, 2026

Owner-Harm: A Missing Threat Model for AI Agent Safety

Dongcheng Zhang, Yiqing Jiang

The paper introduces Owner-Harm, a formal threat model addressing the critical blind spot of AI agents harming their own deployers, demonstrating that specialized defenses are needed beyond generic sa…

View →
cs.CRcs.AIApr 28, 2026

Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills

Lijia Lv, Xuehai Tang, Jie Wen, Jizhong Han +1 more

The paper introduces SkillGuard-Robust, a novel framework for robust, cross-file security auditing of untrusted agent skills, achieving high accuracy on large-scale package evaluations.

View →
cs.LGcs.CLcs.CRMay 14, 2026

LiSA: Lifelong Safety Adaptation via Conservative Policy Induction

Minbeom Kim, Lesly Miculicich, Bhavana Dalvi Mishra, Mihir Parmar +5 more

LiSA introduces a conservative policy induction framework that enhances fixed AI guardrails by converting sparse, noisy failure reports into reusable, generalized policies, significantly improving saf…

View →
cs.CRcs.CLMay 13, 2026

Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution

Xiaozhe Zhang, Chaozhuo Li, Hui Liu, Shaocheng Yan +3 more

The EvoSafety framework enhances LLM safety by externalizing attack and defense mechanisms, enabling persistent, transferable, and model-agnostic robustness against adversarial prompts.

View →
cs.CRcs.AIApr 13, 2026

ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection

Wei Zhao, Zhe Li, Peixin Zhang, Jun Sun

ClawGuard is a novel runtime security framework that deterministically enforces user-confirmed rules at tool-call boundaries to protect LLM agents from indirect prompt injection.

View →
cs.CRcs.AIcs.CLRecentMay 29, 2026

From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors

Jiejun Tan, Zhicheng Dou, Xinyu Yang, Yuyang Hu +3 more

This paper introduces ClawTrojan, a benchmark for multi-step trojan attacks against LLM agents, and proposes DASGuard, a dynamic defense mechanism that traces and sanitizes untrusted control content i…

View →