Pith. sign in

REVIEW 5 cited by

Machine Unlearning for Image-to-Image Generative Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2402.00351 v2 pith:CNEARVIH submitted 2024-02-01 cs.LG cs.CV

Guihong Li , Hsiang Hsu , Chun-Fu Chen , Radu Marculescu This is my paper · ORCID
classification cs.LGcs.CV
keywords unlearningmachinemodelsgenerativesamplesimage-to-imagealgorithmdata
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Machine unlearning has emerged as a new paradigm to deliberately forget data samples from a given model in order to adhere to stringent regulations. However, existing machine unlearning methods have been primarily focused on classification models, leaving the landscape of unlearning for generative models relatively unexplored. This paper serves as a bridge, addressing the gap by providing a unifying framework of machine unlearning for image-to-image generative models. Within this framework, we propose a computationally-efficient algorithm, underpinned by rigorous theoretical analysis, that demonstrates negligible performance degradation on the retain samples, while effectively removing the information from the forget samples. Empirical studies on two large-scale datasets, ImageNet-1K and Places-365, further show that our algorithm does not rely on the availability of the retain samples, which further complies with data retention policy. To our best knowledge, this work is the first that represents systemic, theoretical, empirical explorations of machine unlearning specifically tailored for image-to-image generative models. Our code is available at https://github.com/jpmorganchase/l2l-generator-unlearning.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. 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.

  2. ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models

    cs.CV 2025-07 conditional novelty 6.0 of 10

    ZIUM attacks unlearned diffusion models by optimizing an image-captioning module that turns a target image into a text embedding, then reuses that module zero-shot on unseen images of the same unlearned concept.

  3. SecureT2I: No More Unauthorized Manipulation on AI Generated Images from Prompts

    cs.CR 2025-07 reject novelty 4.0 of 10

    A diffusion editing model is fine-tuned with a blur target for forbidden images and the original output for permitted images, claiming selective suppression of unauthorized edits.

  4. Towards Machine Unlearning for Paralinguistic Speech Processing

    eess.AS 2025-06 conditional novelty 4.0 of 10

    SISA++ uses weight averaging of shard-trained models to outperform SISA in retaining SER and DD performance after user-data unlearning on CREMA-D and E-DAIC.

  5. Realistic Image-to-Image Machine Unlearning via Decoupling and Knowledge Retention

    cs.LG 2025-02 reject novelty 4.0 of 10

    The paper claims that gradient ascent on forget samples makes them out-of-distribution for an unlearned image-to-image model, with formal guarantees and a data-poisoning audit.

Pith tools