Sleeper channels enable persistent prompt injection in always-on AI agents via persistence substrate and firing separation, countered by provenance gates using action digests and owner attestations with a soundness theorem.
The protection of information in computer systems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CR 2years
2026 2roles
background 2polarities
background 2representative citing papers
Multi-agent LLM frameworks can spread compromises across agent boundaries via insecure memory inheritance during subagent spawning.
citing papers explorer
-
Sleeper Channels and Provenance Gates: Persistent Prompt Injection in Always-on Autonomous AI Agents
Sleeper channels enable persistent prompt injection in always-on AI agents via persistence substrate and firing separation, countered by provenance gates using action digests and owner attestations with a soundness theorem.
-
When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks
Multi-agent LLM frameworks can spread compromises across agent boundaries via insecure memory inheritance during subagent spawning.