Skip to content
Sagan

Paper

Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees

Unreadunread

AI summary

arXiv:2606. 24322v1 Announce Type: new Abstract: LLM agents increasingly rely on persistent long-term memory, which creates a critical vulnerability that we study here: memory poisoning.