Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?
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, detect
Record details
Published: 20 July 2026
Source: arXiv cs.AI
Category: Research
Topics: Agents & autonomy · Finance, VC & PE
Retrieved: 21 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?
HuggingFace Daily Papers · 19 July 2026
Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation
arXiv cs.AI · 21 July 2026
Back to the museum: Investigation of the acceptance of Android Andrea with and without emotion simulation in a museum
arXiv cs.HC · 17 July 2026
Recursive Harness Self-Improvement
HuggingFace Daily Papers · 16 July 2026
ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs
arXiv · 15 July 2026
Early Adoption of Agentic Coding Tools by GitHub Projects
arXiv · 15 July 2026
How to cite this record
ethics.ai (20 July 2026), “Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?,” evidence record 12219, https://ethics.ai/record/12219 (originally published by arXiv cs.AI).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.