works on
adaptive learning 1agent architecture 1autonomous systems 1foundation models 1self-improving agents 1

From the 1 of 10 linked papers with an AI index.

collaborators
Showing cs.CRShow all

1 paper · 1 filter

cs.CR2026

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

Yimeng Chen, Nathanaël Denis, Roberto Di Pietro +1

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…