MRMMIA is a multi-recall-probe membership inference attack that extracts signals from chat agent memory and outperforms baselines in black-, gray-, and white-box settings.
Available: https://arxiv.org/abs/2406.19234
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
PPE framework with T3+OCSVM one-class detector reaches 0.93+ borderline AUROC, cuts false positives 44-55 points versus Gaussian baselines, and runs at millisecond latency on synthetic multi-domain data.
citing papers explorer
-
MRMMIA: Membership Inference Attacks on Memory in Chat Agents
MRMMIA is a multi-recall-probe membership inference attack that extracts signals from chat agent memory and outperforms baselines in black-, gray-, and white-box settings.
-
Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation
PPE framework with T3+OCSVM one-class detector reaches 0.93+ borderline AUROC, cuts false positives 44-55 points versus Gaussian baselines, and runs at millisecond latency on synthetic multi-domain data.