Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914310390808576 |
|---|---|
| author | Yu, Zhenxiong Yang, Zhi Jin, Zhiheng Wang, Shuhe Zhang, Heng Fei, Yanlin Zeng, Lingfeng Lou, Fangqi Zhang, Shuo Hu, Tu Liu, Jingping Chen, Rongze Zhu, Xingyu Wang, Kunyi Yuan, Chaofa Guo, Xin Liu, Zhaowei Zhang, Feipeng Huang, Jie Wang, Huacan Chen, Ronghao Zhang, Liwen |
| author_facet | Yu, Zhenxiong Yang, Zhi Jin, Zhiheng Wang, Shuhe Zhang, Heng Fei, Yanlin Zeng, Lingfeng Lou, Fangqi Zhang, Shuo Hu, Tu Liu, Jingping Chen, Rongze Zhu, Xingyu Wang, Kunyi Yuan, Chaofa Guo, Xin Liu, Zhaowei Zhang, Feipeng Huang, Jie Wang, Huacan Chen, Ronghao Zhang, Liwen |
| contents | 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$^2$Bench, 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\%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05386 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening Yu, Zhenxiong Yang, Zhi Jin, Zhiheng Wang, Shuhe Zhang, Heng Fei, Yanlin Zeng, Lingfeng Lou, Fangqi Zhang, Shuo Hu, Tu Liu, Jingping Chen, Rongze Zhu, Xingyu Wang, Kunyi Yuan, Chaofa Guo, Xin Liu, Zhaowei Zhang, Feipeng Huang, Jie Wang, Huacan Chen, Ronghao Zhang, Liwen Cryptography and Security Artificial Intelligence 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$^2$Bench, 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\%. |
| title | Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2602.05386 |