Pith. sign in

REVIEW 10 cited by

Machine Unlearning of Features and Labels

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 2108.11577 v4 pith:LVXQ46IK submitted 2021-08-26 cs.LG cs.CR

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

Removing information from a machine learning model is a non-trivial task that requires to partially revert the training process. This task is unavoidable when sensitive data, such as credit card numbers or passwords, accidentally enter the model and need to be removed afterwards. Recently, different concepts for machine unlearning have been proposed to address this problem. While these approaches are effective in removing individual data points, they do not scale to scenarios where larger groups of features and labels need to be reverted. In this paper, we propose the first method for unlearning features and labels. Our approach builds on the concept of influence functions and realizes unlearning through closed-form updates of model parameters. It enables to adapt the influence of training data on a learning model retrospectively, thereby correcting data leaks and privacy issues. For learning models with strongly convex loss functions, our method provides certified unlearning with theoretical guarantees. For models with non-convex losses, we empirically show that unlearning features and labels is effective and significantly faster than other strategies.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

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

  1. BadFU: Backdoor Federated Learning through Adversarial Machine Unlearning

    cs.CR 2025-08 conditional novelty 6.0 of 10

    A malicious federated-learning client can hide a backdoor by adding trigger-labeled samples plus camouflage samples, then activate it by requesting unlearning of the camouflage samples.

  2. Towards Source-Free Machine Unlearning

    cs.LG 2025-08 conditional novelty 6.0 of 10

    A Hessian estimation procedure using only the forget set enables instance-level source-free unlearning with claimed theoretical error bounds.

  3. Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design

    cs.CR 2025-08 conditional novelty 6.0 of 10

    Water4MU tunes an invisible watermark on data so that machine unlearning algorithms can remove requested images more effectively, beating prior methods on 'challenging forgets'.

  4. LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning

    cs.LG 2025-07 conditional novelty 6.0 of 10

    LoReUn, a plug-in loss-based reweighting strategy, improves approximate machine unlearning by focusing updates on hard-to-forget low-loss data points.

  5. Zero-Shot Machine Unlearning with Proxy Adversarial Data Generation

    cs.LG 2025-07 conditional novelty 6.0 of 10

    ZS-PAG generates adversarial proxy samples from the forget set, projects unlearning updates into the orthogonal complement of remaining-class subspaces, and optimizes pseudo-labels with influence functions to enable z...

  6. On the Necessity of Output Distribution Reweighting for Effective Class Unlearning

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Class unlearning methods leak membership through neighbor-class output probabilities, and a tilted reweighting objective that mimics retrained models reduces this leakage.

  7. Module-Aware Parameter-Efficient Machine Unlearning on Transformers

    cs.LG 2025-08 conditional novelty 5.0 of 10

    MAPE-Unlearn uses Fisher-information-based scores and greedy search to select important heads and filters, then applies sparse unlearning updates, claiming improved efficacy-fidelity trade-offs on Transformers.

  8. SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks

    cs.CR 2025-06 conditional novelty 5.0 of 10

    SOFT paraphrases low-loss fine-tuning samples before training, reducing MIA AUC from about 0.82 to about 0.54 across six datasets at roughly 7% perplexity cost.

  9. Membership Inference Attacks with False Discovery Rate Control

    stat.ML 2025-08 conditional novelty 4.0 of 10

    A post-hoc wrapper, MIAFdR, converts any membership inference attack scores into conformal p-values and applies a Benjamini-Hochberg correction, guaranteeing that the expected proportion of non-members among flagged m...

  10. Leveraging Distribution Matching to Make Approximate Machine Unlearning Faster

    cs.LG 2025-07 reject novelty 4.0 of 10

    A dual data and loss-centric method claims to speed up machine unlearning, but its MIA regularizer cancels itself and the test set is leaked into training.

Pith tools