arXiv cs.CL· Asif Shahriar, Md Nafiu Rahman, Sadif Ahmed, Farig Sadeque, Md Rizwan Parvez·· 11 小时前AI 评分38
智能体安全综述：应用、威胁与防御
A Survey on Agentic Security: Applications, Threats and Defenses
AI 导读
一篇被 TMLR 2026 接收的综述首次系统梳理智能体安全领域，围绕应用、威胁与防御三大支柱构建分类体系，覆盖 274 篇论文。研究涵盖红队与蓝队智能体、智能体系统攻击面、防御技术及攻防评估框架，并量化分析攻击入口与智能体循环阶段、防御策略的成本与安全权衡。交叉分析还映射了防御与攻击类别的覆盖关系，并梳理智能体架构、基座模型使用与数据模态的趋势。
正文 · 原文
Abstract:In this work we present the first holistic survey of the agentic security landscape, structuring the field around the fundamental pillars of Applications, Threats and Defenses. We provide a comprehensive taxonomy of 274 papers that covers red-teaming, blue-teaming and domain-specific applications, attack surfaces on agentic systems, defense techniques, and both offensive and defensive evaluation frameworks. For each pillar, we first discuss the literature around the taxonomy and then perform a quantitative analysis to understand the patterns across these works. For the applications, we show their security-lifecycle coverage map, compare between red-teaming and blue-teaming agents, and analyze the adversarial use of red-teaming applications. On the threat side, we analyze the entry points and agent-loop stages that attacks target, their specificity to the agentic setting, and the threat models they assume. On the defense side, we analyze the prevailing defense strategies, their cost and security trade-offs, and where in the agent lifecycle they are deployed. Finally, we provide a deatiled cross-cutting analysis, where we map which defenses cover which attack classes and chart trends in agent architecture, backbone model usage, and data modality coverage. Taken together, these findings give a researcher a structural understanding of how agentic capabilities, vulnerabilities, and countermeasures relate to one another, and to identify where the field is concentrated and where it is thin.
| Comments: | Transactions on Machine Learning Research (TMLR) 2026 |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR) |
| Cite as: | arXiv:2510.06445 [cs.CL] |
| (or arXiv:2510.06445v4 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2510.06445 arXiv-issued DOI via DataCite |
Submission history
From: Asif Shahriar [view email]
[v1]
Tue, 7 Oct 2025 20:32:20 UTC (102 KB)
[v2]
Sat, 20 Dec 2025 13:42:00 UTC (81 KB)
[v3]
Fri, 12 Jun 2026 21:57:35 UTC (2,027 KB)
[v4]
Sat, 31 Oct 2026 19:41:43 UTC (887 KB)
来源：arXiv cs.CL · arxiv.org