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
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.
Forward citations
Cited by 10 Pith papers
-
BadFU: Backdoor Federated Learning through Adversarial Machine Unlearning
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.
-
Towards Source-Free Machine Unlearning
A Hessian estimation procedure using only the forget set enables instance-level source-free unlearning with claimed theoretical error bounds.
-
Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design
Water4MU tunes an invisible watermark on data so that machine unlearning algorithms can remove requested images more effectively, beating prior methods on 'challenging forgets'.
-
LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning
LoReUn, a plug-in loss-based reweighting strategy, improves approximate machine unlearning by focusing updates on hard-to-forget low-loss data points.
-
Zero-Shot Machine Unlearning with Proxy Adversarial Data Generation
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...
-
On the Necessity of Output Distribution Reweighting for Effective Class Unlearning
Class unlearning methods leak membership through neighbor-class output probabilities, and a tilted reweighting objective that mimics retrained models reduces this leakage.
-
Module-Aware Parameter-Efficient Machine Unlearning on Transformers
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.
-
SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks
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.
-
Membership Inference Attacks with False Discovery Rate Control
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...
-
Leveraging Distribution Matching to Make Approximate Machine Unlearning Faster
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.
Discussion (0). Sign in to comment.