Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Yimeng Chen

Yimeng Chen

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Crypto×1AI×1NLP×1Multiagent×1

Frequent co-authors

Nathanaël Denis1×
Roberto Di Pietro1×
Jürgen Schmidhuber1×

Research Timeline

2026
Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?

This paper investigates the OS resilience to a new class of attacks called self-state attacks, where an agent's state is compromised via legitimate OS system call invocation. It characterizes the attack space, evaluates prevention, detection, and recovery strategies, and introduces a workload-conditioned view of detectability.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.CLEmpiricalRecentJul 20, 2026

Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?

Yimeng Chen, Nathanaël Denis, Roberto Di Pietro, Jürgen Schmidhuber

This paper investigates the OS resilience to a new class of attacks called self-state attacks, where an agent's state is compromised via legitimate OS system call invocation. It characterizes the atta…

View →