https://arxivexplained.com/papers/spider-sense-intrinsic-risk-sensing-for-efficient-agent-defense-with-hierarchical-adaptive-screening\n","updatedAt":"2026-02-06T21:05:06.239Z","author":{"_id":"65d9fc2a0e6ad24551d87a1e","avatarUrl":"/avatars/3aedb9522cc3cd08349d654f523fd792.svg","fullname":"Grant Singleton","name":"grantsing","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":4,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7031875252723694},"editors":["grantsing"],"editorAvatarUrls":["/avatars/3aedb9522cc3cd08349d654f523fd792.svg"],"reactions":[],"isReport":false}},{"id":"6986579c661b7c0fa18fb234","author":{"_id":"65243980050781c16f234f1f","avatarUrl":"/avatars/743a009681d5d554c27e04300db9f267.svg","fullname":"Avi","name":"avahal","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":3,"isUserFollowing":false},"createdAt":"2026-02-06T21:05:32.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"arXivLens breakdown of this paper 👉 https://arxivlens.com/PaperView/Details/spider-sense-intrinsic-risk-sensing-for-efficient-agent-defense-with-hierarchical-adaptive-screening-6462-36111177\n- Executive Summary\n- Detailed Breakdown\n- Practical Applications","html":"
arXivLens breakdown of this paper 👉 https://arxivlens.com/PaperView/Details/spider-sense-intrinsic-risk-sensing-for-efficient-agent-defense-with-hierarchical-adaptive-screening-6462-36111177
\n- \n
- Executive Summary \n
- Detailed Breakdown \n
- Practical Applications \n
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
\nThe following papers were recommended by the Semantic Scholar API
\n- \n
- VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit (2026) \n
- FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments (2026) \n
- SHIELD: An Auto-Healing Agentic Defense Framework for LLM Resource Exhaustion Attacks (2026) \n
- ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback (2026) \n
- Risky-Bench: Probing Agentic Safety Risks under Real-World Deployment (2026) \n
- BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents (2026) \n
- AgenTRIM: Tool Risk Mitigation for Agentic AI (2026) \n
Please give a thumbs up to this comment if you found it helpful!
\nIf you want recommendations for any Paper on Hugging Face checkout this Space
\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
Papers
arxiv:2602.05386
Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening
Abstract
Spider-Sense framework provides intrinsic and selective agent security through event-driven defense with intrinsic risk sensing, achieving low attack success and false positive rates with minimal latency overhead.
AI-generated summary
As large language models (LLMs) evolve into autonomous agents, their real-world applicability has expanded significantly, accompanied by new security challenges. Most existing agent defense mechanisms adopt a mandatory checking paradigm, in which security validation is forcibly triggered at predefined stages of the agent lifecycle. In this work, we argue that effective agent security should be intrinsic and selective rather than architecturally decoupled and mandatory. We propose Spider-Sense framework, an event-driven defense framework based on Intrinsic Risk Sensing (IRS), which allows agents to maintain latent vigilance and trigger defenses only upon risk perception. Once triggered, the Spider-Sense invokes a hierarchical defence mechanism that trades off efficiency and precision: it resolves known patterns via lightweight similarity matching while escalating ambiguous cases to deep internal reasoning, thereby eliminating reliance on external models. To facilitate rigorous evaluation, we introduce S^2Bench, a lifecycle-aware benchmark featuring realistic tool execution and multi-stage attacks. Extensive experiments demonstrate that Spider-Sense achieves competitive or superior defense performance, attaining the lowest Attack Success Rate (ASR) and False Positive Rate (FPR), with only a marginal latency overhead of 8.3\%.
Community
Endow AI Agents with "Spider-Sense"! Spider-Sense: Pioneering Intrinsic Risk Sensing, Reducing Defense Delay to 8.3%
arXiv explained breakdown of this paper 👉 https://arxivexplained.com/papers/spider-sense-intrinsic-risk-sensing-for-efficient-agent-defense-with-hierarchical-adaptive-screening
arXivLens breakdown of this paper 👉 https://arxivlens.com/PaperView/Details/spider-sense-intrinsic-risk-sensing-for-efficient-agent-defense-with-hierarchical-adaptive-screening-6462-36111177
- Executive Summary
- Detailed Breakdown
- Practical Applications
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit (2026)
- FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments (2026)
- SHIELD: An Auto-Healing Agentic Defense Framework for LLM Resource Exhaustion Attacks (2026)
- ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback (2026)
- Risky-Bench: Probing Agentic Safety Risks under Real-World Deployment (2026)
- BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents (2026)
- AgenTRIM: Tool Risk Mitigation for Agentic AI (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2602.05386 in a model README.md to link it from this page.
Datasets citing this paper 1
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2602.05386 in a Space README.md to link it from this page.