自托管AI代理的自我状态攻击：操作系统防御能走多远？

摘要

自托管AI代理通过读写自身的内存和配置文件来实现功能。代理可能因其自身状态的损坏而遭到入侵——这种入侵通过合法的操作系统系统调用实现。我们将其称为自状态攻击威胁类别。本文研究了操作系统对此类攻击的韧性。我们正式表征了一个四轴攻击空间（目标、机制、粒度、时间性）；探讨了预防、检测和恢复的结构性局限；并引入了基于工作负载条件的可检测性视角。为将该框架实例化，我们从运行于不同工作负载画像下的代表性自托管代理中收集了实时活动轨迹，并将攻击空间实现为一个23单元格矩阵，包含43个针对真实自状态文件的具体操作，并将这些操作注入轨迹中。随后，我们评估了经典防御策略和工作负载条件化防御策略。实证结果表明，分层防御体系（指令与配置层的访问控制预防、内存层的工作负载条件化检测、以及用于恢复的周期性备份）对大多数攻击单元格有效，但仍有少量残留攻击面在操作系统层面结构上无法区分。这些发现表明，针对新确立的自状态攻击类别，操作系统层面的防御需要重新审视，并可能为这一领域开辟新的研究方向。

English

Self-hosted AI agents read and write their own memory and configuration files to function. An agent may get compromised via corruption of its own state -- a compromise realized via legitimate OS system call invocation. We refer to this class of threats as self-state attacks. In this paper, we investigate the OS resilience to this class of attacks. Formally, we characterize a four-axis attack space (Target, Mechanism, Granularity, Temporal); investigate the structural limits of prevention, detection, and recovery; and introduce a workload-conditioned view of detectability. To instantiate the framework, we collect live activity traces from a representative self-hosted agent running across distinct workload profiles, and realize the attack space as a 23-cell matrix, 43 concrete operations on real self-state files, and injected into those traces. We then evaluate both canonical and workload-conditioned defense strategies. The empirical results show that a layered defense stack (access-control prevention on the instruction and configuration layers, workload-conditioned detection on the memory layer, and periodic backup for recovery) is effective on most attack cells while a small residual attack surface remains structurally indistinguishable at the OS level. These findings suggest that against the newly established class of self-state attacks, OS-level defense needs to be reconsidered, potentially opening new research directions in the field.