Pith. sign in

REVIEW 2 cited by

PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding

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 2407.02943 v2 pith:Z7757TQJ submitted 2024-07-03 cs.CR cs.AIcs.CLcs.LG

Krishna Kanth Nakka , Ahmed Frikha , Ricardo Mendes , Xue Jiang , Xuebing Zhou This is my paper
classification cs.CRcs.AIcs.CLcs.LG
keywords dataextractiongroundingmodelsnumberphonepii-compasstraining
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The latest and most impactful advances in large models stem from their increased size. Unfortunately, this translates into an improved memorization capacity, raising data privacy concerns. Specifically, it has been shown that models can output personal identifiable information (PII) contained in their training data. However, reported PIII extraction performance varies widely, and there is no consensus on the optimal methodology to evaluate this risk, resulting in underestimating realistic adversaries. In this work, we empirically demonstrate that it is possible to improve the extractability of PII by over ten-fold by grounding the prefix of the manually constructed extraction prompt with in-domain data. Our approach, PII-Compass, achieves phone number extraction rates of 0.92%, 3.9%, and 6.86% with 1, 128, and 2308 queries, respectively, i.e., the phone number of 1 person in 15 is extractable.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

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

  1. 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.

  2. Understanding and Mitigating Cross-lingual Privacy Leakage via Language-specific and Universal Privacy Neurons

    cs.CL 2025-06 reject novelty 6.0 of 10

    Cross-lingual privacy leakage in LLMs is driven by a mix of language-universal and language-specific neurons, and deactivating those neurons lowers measured leakage by 23.3% to 31.6%.

Pith tools