AI & ML
Forget the Lineage: Forward-Secure, Lineage-Complete Cryptographic Erasure for LLM-Agent Memory
arXiv cs.CR0 views
arXiv:2611.18133v1 Announce Type: new Abstract: 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. We define lineage-complete forward-secure erasure: after a forget request, an adversary that later obtains all storage and the agent's current keys learns nothing about the forgotten input or any memory derived from it. We present LinEra, which encrypts each memory under a key derived from its parents' keys along the derivation graph; source keys come from a puncturable pseudorandom function, so forgetting is a single puncture and every descendant becomes unreadable without being located. A sound lineage rule records as parents everything the writer saw, which confines all influence of a source to its descendants. We prove security and lineage integrity and integrate LinEra with mem0. With real LLMs from two families (1.5B to 7B parameters) writing the memory of LoCoMo conversations, an attacker holding every file and the current keys recovers, on all ten conversations written by the largest model, 70 of 71 forgotten secrets after logical deletion, 67 with per-object or epoch keys, and none with LinEra; the same holds for every writer tested. The price is a larger forgetting radius, which follows a simple law in the writer's fan-in: forgetting 1% of turns erases 73.0% of derived memories with session-level summaries but only 3.8% with four-turn windows, which also answer better; re-deriving restores what is lost.
Source:https://arxiv.org/abs/2611.18133PreviousHello Again: Exploiting Replay Protected Monotonic Counters to Brute-Force Windows Hello PINsNextFrom Bytes to Behavior: Request-Level Attribution from Live GPU Hidden States
Related posts
Building an AI Agent Backend with FastAPI: From User Request to AI Response
0dev.to AI

SoduWork Custom Model Setup: Connect an OpenAI-Compatible Gateway and Handle the 180-Second Stall
0dev.to AI
AI startup hiring snapshot, 16 November 2026: 6,481 open roles, half at four companies
0dev.to AI
EC2 已经停止,账单为什么还在变?用资源清单代替猜测
0dev.to AWS

Amazon Black Friday 2026:5 Key Metrics and a Step-by-Step Data Collection Guide
0dev.to AWS
How to Trim Audio for an Online Course Lesson — Free, in Your Browser
0dev.to WebDev