Pith. sign in

REVIEW 1 cited by

Tight Auditing of Differentially Private Machine Learning

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 2302.07956 v1 pith:OFSQXFBB submitted 2023-02-15 cs.LG cs.CR

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

Auditing mechanisms for differential privacy use probabilistic means to empirically estimate the privacy level of an algorithm. For private machine learning, existing auditing mechanisms are tight: the empirical privacy estimate (nearly) matches the algorithm's provable privacy guarantee. But these auditing techniques suffer from two limitations. First, they only give tight estimates under implausible worst-case assumptions (e.g., a fully adversarial dataset). Second, they require thousands or millions of training runs to produce non-trivial statistical estimates of the privacy leakage. This work addresses both issues. We design an improved auditing scheme that yields tight privacy estimates for natural (not adversarially crafted) datasets -- if the adversary can see all model updates during training. Prior auditing works rely on the same assumption, which is permitted under the standard differential privacy threat model. This threat model is also applicable, e.g., in federated learning settings. Moreover, our auditing scheme requires only two training runs (instead of thousands) to produce tight privacy estimates, by adapting recent advances in tight composition theorems for differential privacy. We demonstrate the utility of our improved auditing schemes by surfacing implementation bugs in private machine learning code that eluded prior auditing techniques.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 14 citations worldwide. Full citation record

  1. Curator Attack: When Blackbox Differential Privacy Auditing Loses Its Power

    cs.CR 2024-11 conditional novelty 7.0 of 10

    Blackbox DP auditors that ignore small-probability outputs systematically fail to detect privacy violations, enabling curator attacks that pass overstated privacy claims.

Pith tools