Skip to content
NewA calmer, faster ZeroHour

LinEra erases LLM-agent memory derivatives with one key puncture

Original title: Forget the Lineage: Forward-Secure, Lineage-Complete Cryptographic Erasure for LLM-Agent Memory

arXiv cs.CRby Yulliwas Ameur ()1 min read
AI summary · x-ai/grok-4.7Summaries by Vani AI

With every file and the current keys, an attacker recovered none of 71 forgotten secrets under LinEra.

The paper defines lineage-complete forward-secure erasure so a later holder of storage and current keys learns nothing about a forgotten input or memories derived from it. LinEra encrypts each memory under a key derived from its parents and forgets by puncturing a pseudorandom function, making descendants unreadable without locating them. It was integrated with mem0 and tested as models from 1.5B to 7B parameters wrote LoCoMo conversation memory.

Key facts
  • Logical deletion left 70 of 71 secrets recoverable on the largest model.
  • Per-object or epoch keys still left 67 of 71 recoverable.
  • Forgetting 1% of turns erased 73.0% of memories with session summaries.
  • Four-turn windows limited collateral erasure to 3.8% and answered better.
  • Re-deriving restores memories lost to the larger forgetting radius.
Analyze this story with Vani AIImpact, who is affected and what defenders should do, in a new chat

From the original article

1 min read at arxiv.org

Large language model (LLM) agents keep a long-term memory that the model itself writes: summaries, extracted facts and embeddings derived from what users said. Deleting a message is therefore not enough: its derivatives, storage residue and backups survive.

arXiv cs.CR

By Yulliwas Ameur · arxiv.org

Read the full article at arXiv cs.CR

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.