Pith. sign in

REVIEW 2 cited by

Adaptive Machine Unlearning

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 2106.04378 v1 pith:QGDZNN3K submitted 2021-06-08 cs.LG stat.ML

classification cs.LGstat.ML
keywords deletionsequencesmodelsadaptiveguaranteesdatapriorwork
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Data deletion algorithms aim to remove the influence of deleted data points from trained models at a cheaper computational cost than fully retraining those models. However, for sequences of deletions, most prior work in the non-convex setting gives valid guarantees only for sequences that are chosen independently of the models that are published. If people choose to delete their data as a function of the published models (because they don't like what the models reveal about them, for example), then the update sequence is adaptive. In this paper, we give a general reduction from deletion guarantees against adaptive sequences to deletion guarantees against non-adaptive sequences, using differential privacy and its connection to max information. Combined with ideas from prior work which give guarantees for non-adaptive deletion sequences, this leads to extremely flexible algorithms able to handle arbitrary model classes and training methodologies, giving strong provable deletion guarantees for adaptive deletion sequences. We show in theory how prior work for non-convex models fails against adaptive deletion sequences, and use this intuition to design a practical attack against the SISA algorithm of Bourtoule et al. [2021] on CIFAR-10, MNIST, Fashion-MNIST.

Discussion (0). Continue with ORCID 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. System-Aware Unlearning Algorithms: Use Lesser, Forget Faster

    cs.LG 2025-06 conditional novelty 7.0 of 10

    The paper introduces system-aware unlearning and gives the first exact unlearning algorithm for linear classification that stores a sublinear-size core set instead of the entire dataset.

  2. Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness

    cs.LG 2025-06 conditional novelty 6.0 of 10

    IAM interpolates between an original model and a shadow model to score each sample's unlearning completeness, achieving top AUC for exact unlearning and top correlation for approximate unlearning, and exposing under- ...

Pith tools