Agent Security is a Systems Problem
Authors: Mihai Christodorescu, Earlence Fernandes, Ashish Hooda et al.
Summary
arXiv:2605. 18991v1 Announce Type: new 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.
Relevance
Read next because Agent Security is a Systems Problem overlaps with experiment "Implement Chen et al. persona-vector extraction recipe and compare to project's centroid-difference recipe", experiment "#351 follow-up: broader-vocab position-0 sweep at T=1.0 + position-1 suffix isolation", experiment "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: implement, position, model. Source: arxiv cs.CR (Cryptography and Security).
Threat model
Potential threat/caveat for experiment "Implement Chen et al. persona-vector extraction recipe and compare to project's centroid-difference recipe": this item discusses robustness, adversarial.
Abstract
arXiv:2605.18991v1 Announce Type: new 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.