OS-level defenses against self-hosted AI agents that corrupt their own memory/config files can close most attack cells but cannot detect small in-distribution memory edits, leaving a residual surface.
InInternational Symposium on Methodologies for Intelligent Sys- tems (ISMIS) (Lecture Notes in Computer Science 3488)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?
OS-level defenses against self-hosted AI agents that corrupt their own memory/config files can close most attack cells but cannot detect small in-distribution memory edits, leaving a residual surface.