Pith. sign in

REVIEW 7 cited by

Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2203.03929 v2 pith:PWELKFEV submitted 2022-03-08 cs.LG cs.AIcs.CR

classification cs.LGcs.AIcs.CR
keywords attacksinferencemembershipmlmsattackmodelspriorprivacy
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The wide adoption and application of Masked language models~(MLMs) on sensitive data (from legal to medical) necessitates a thorough quantitative investigation into their privacy vulnerabilities -- to what extent do MLMs leak information about their training data? Prior attempts at measuring leakage of MLMs via membership inference attacks have been inconclusive, implying the potential robustness of MLMs to privacy attacks. In this work, we posit that prior attempts were inconclusive because they based their attack solely on the MLM's model score. We devise a stronger membership inference attack based on likelihood ratio hypothesis testing that involves an additional reference MLM to more accurately quantify the privacy risks of memorization in MLMs. We show that masked language models are extremely susceptible to likelihood ratio membership inference attacks: Our empirical results, on models trained on medical notes, show that our attack improves the AUC of prior membership inference attacks from 0.66 to an alarmingly high 0.90 level, with a significant improvement in the low-error region: at 1% false positive rate, our attack is 51X more powerful than prior work.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 10 citations worldwide. Full citation record

  1. In-Context Probing for Membership Inference in Fine-Tuned Language Models

    cs.CR 2025-12 conditional novelty 6.0 of 10

    ICP-MIA infers membership in fine-tuned LLMs by measuring confidence improvement under in-context probes, beating prior black-box attacks at low false-positive rates.

  2. LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems

    cs.CR 2025-09 conditional novelty 6.0 of 10

    A systematic review that categorizes LLM threats, severity scores, and mitigations across development and operation life cycles and multiple deployment scenarios.

  3. Ensembling Membership Inference Attacks Against Tabular Generative Models

    cs.CR 2025-09 conditional novelty 6.0 of 10

    No single membership inference attack dominates across tabular generative models, and unsupervised ensembles of attacks achieve better average rankings.

  4. Evaluating the Dynamics of Membership Privacy in Deep Learning

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Per-sample membership vulnerability is established early in training, especially for hard-to-learn examples, and can be tracked on an FPR-TPR plane.

  5. Identifying Pre-training Data in LLMs: A Neuron Activation-Based Detection Framework

    cs.AI 2025-07 reject novelty 6.0 of 10

    NA-PDD detects pre-training data in LLMs by comparing which neurons activate for a test text against neurons linked to known training versus non-training texts, and claims large AUC improvements on three benchmarks.

  6. Membership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemble

    cs.LG 2025-06 conditional novelty 6.0 of 10

    MIAs expose different members depending on attack method and random seed; the paper quantifies this with coverage/stability and shows ensembling attacks yields stronger, more reliable privacy checks.

  7. Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning

    cs.CR 2025-06

Pith tools