Pith. sign in

REVIEW 6 cited by

Are Large Pre-Trained Language Models Leaking Your Personal Information?

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2205.12628 v2 pith:32WBTGPT submitted 2022-05-25 cs.CL cs.AIcs.CR

Jie Huang , Hanyin Shao , Kevin Chen-Chuan Chang This is my paper
classification cs.CLcs.AIcs.CR
keywords informationpersonalplmsmodelslanguageleakingpre-trainedemail
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Are Large Pre-Trained Language Models Leaking Your Personal Information? In this paper, we analyze whether Pre-Trained Language Models (PLMs) are prone to leaking personal information. Specifically, we query PLMs for email addresses with contexts of the email address or prompts containing the owner's name. We find that PLMs do leak personal information due to memorization. However, since the models are weak at association, the risk of specific personal information being extracted by attackers is low. We hope this work could help the community to better understand the privacy risk of PLMs and bring new insights to make PLMs safe.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Rethinking Memorization Measures and their Implications in Large Language Models

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Contextual memorization, defined by comparing a string's training loss against the best loss without training on that string, is stricter than counterfactual memorization and suggests that zero-memorization optimal le...

  2. What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests

    cs.CL 2025-07 conditional novelty 6.0 of 10

    WikiMem, a Wikidata-derived canary dataset and a calibrated NLL-ranking metric, identifies which human-fact associations an LLM has memorized, with higher rates for famous people and larger models.

  3. ISACL: Internal State Analyzer for Copyrighted Training Data Leakage

    cs.CL 2025-08 conditional novelty 5.0 of 10

    An MLP trained on LLM internal states predicts Rouge-L-defined literal copying leakage with high accuracy, but not paraphrase-level leakage.

  4. From Teacher to Student: Tracking Memorization Through Model Distillation

    cs.LG 2025-06 conditional novelty 5.0 of 10

    Distillation of fine-tuned GPT-2 teachers into smaller students lowers verbatim memorization of training responses compared to direct fine-tuning, with reverse-KL giving the lowest rates.

  5. A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives

    cs.CR 2025-08 conditional novelty 4.0 of 10

    The paper classifies model extraction attacks and defenses into attack, defense, and computing environment categories and surveys their current state.

  6. A Survey on Model Extraction Attacks and Defenses for Large Language Models

    cs.CR 2025-06 conditional novelty 4.0 of 10

    A taxonomy of model extraction attacks and defenses for large language models, with proposed evaluation metrics and future research directions.

Pith tools