Pith. sign in

REVIEW 3 cited by

Privacy Auditing of Large Language Models

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 2503.06808 v1 pith:CJA6FM66 submitted 2025-03-09 cs.CR cs.AIcs.LG

classification cs.CRcs.AIcs.LG
keywords privacycanariesmodelsauditingllmsmodelpriorapproach
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Current techniques for privacy auditing of large language models (LLMs) have limited efficacy -- they rely on basic approaches to generate canaries which leads to weak membership inference attacks that in turn give loose lower bounds on the empirical privacy leakage. We develop canaries that are far more effective than those used in prior work under threat models that cover a range of realistic settings. We demonstrate through extensive experiments on multiple families of fine-tuned LLMs that our approach sets a new standard for detection of privacy leakage. For measuring the memorization rate of non-privately trained LLMs, our designed canaries surpass prior approaches. For example, on the Qwen2.5-0.5B model, our designed canaries achieve $49.6\%$ TPR at $1\%$ FPR, vastly surpassing the prior approach's $4.2\%$ TPR at $1\%$ FPR. Our method can be used to provide a privacy audit of $\varepsilon \approx 1$ for a model trained with theoretical $\varepsilon$ of 4. To the best of our knowledge, this is the first time that a privacy audit of LLM training has achieved nontrivial auditing success in the setting where the attacker cannot train shadow models, insert gradient canaries, or access the model at every iteration.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run

    cs.CR 2025-07 conditional novelty 6.0 of 10

    UniAud uses synthetic uncorrelated canaries and self-comparison inference to reach near-optimal empirical epsilon lower bounds in one black-box DP audit run, while UniAud++ improves the utility-auditing trade-off via ...

  2. The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A new 8TB openly-licensed text corpus trains 7B LLMs that are competitive with Llama 1/2, showing that performant models need not depend on unlicensed web data.

  3. Efficient Machine Unlearning by Model Splitting and Core Sample Selection

    cs.LG 2025-05 conditional novelty 6.0 of 10

    MAXRR trains the feature extractor on core samples only, so under a generalized unlearning definition, deleting non-core samples is exact and deleting core samples needs only a cheap SVM retrain.

Pith tools