Pith. sign in

REVIEW 1 cited by

Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent

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 2206.02617 v7 pith:FOIHYSL5 submitted 2022-06-06 cs.LG cs.CRcs.DSstat.ML

classification cs.LGcs.CRcs.DSstat.ML
keywords privacyguaranteesindividualprivateaccuracyalgorithmclassdescent
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Differentially private stochastic gradient descent (DP-SGD) is the workhorse algorithm for recent advances in private deep learning. It provides a single privacy guarantee to all datapoints in the dataset. We propose output-specific $(\varepsilon,\delta)$-DP to characterize privacy guarantees for individual examples when releasing models trained by DP-SGD. We also design an efficient algorithm to investigate individual privacy across a number of datasets. We find that most examples enjoy stronger privacy guarantees than the worst-case bound. We further discover that the training loss and the privacy parameter of an example are well-correlated. This implies groups that are underserved in terms of model utility simultaneously experience weaker privacy guarantees. For example, on CIFAR-10, the average $\varepsilon$ of the class with the lowest test accuracy is 44.2\% higher than that of the class with the highest accuracy.

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. Full citation record

  1. Laplace Sample Information: Data Informativeness Through a Bayesian Lens

    cs.LG 2025-05 conditional novelty 6.0 of 10

    LSI ranks training samples by informativeness using the KL divergence between Laplace-approximated posteriors with and without each sample, and the ordering transfers from a small probe to larger models.

Pith tools