Agent Security Is a Systems Problem

Researchers argue that AI agent security must be treated as a systems-level problem, with the AI model itself considered an untrusted component and security invariants enforced at the system level rather than through model robustness alone. The team, drawing on expertise in operating systems, networks, formal methods, and adversarial machine learning, analyzed 11 real-world attacks on agents to demonstrate how established systems security principles could have prevented those breaches. The findings identify key research challenges for implementing these principles in agentic systems.

Computer Science Cryptography and Security Submitted on 18 May 2026 v1 https://arxiv.org/abs/2605.18991v1 , last revised 20 May 2026 this version, v2 Title:Agent Security is a Systems Problem View PDF /pdf/2605.18991 HTML experimental https://arxiv.org/html/2605.18991v2 Abstract:We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants must be enforced at the system level. Through this lens, efforts to increase model robustness the dominant viewpoint in the community are insufficient on their own. Instead, we must complement existing efforts with techniques from the systems security domain. Based on our experience as cybersecurity researchers in operating systems, networks, formal methods, and adversarial machine learning, we articulate a set of core principles, grounded in decades of systems security research, that provide a foundation for designing agentic systems with predictable guarantees. As evidence, we analyze eleven representative real-world attacks on agents and discuss how systems principles, if realized, could have prevented these attacks. We also identify the research challenges that stand in the way of implementing these principles in agents. Submission history From: Nils Palumbo view email /show-email/5bcd5d2c/2605.18991 Mon, 18 May 2026 18:11:17 UTC 9,744 KB v1 /abs/2605.18991v1 v2 Wed, 20 May 2026 17:25:38 UTC 9,744 KB References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .