Pith. sign in

REVIEW 4 cited by

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts

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 2410.12777 v2 pith:IPSONK52 submitted 2024-10-16 cs.CV cs.CLcs.CRcs.LG

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts

classification cs.CV cs.CLcs.CRcs.LG
keywords conceptsunlearnedmeta-unlearningdiffusionfinetuningmodelsrelearningbenign
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

With the rapid progress of diffusion-based content generation, significant efforts are being made to unlearn harmful or copyrighted concepts from pretrained diffusion models (DMs) to prevent potential model misuse. However, it is observed that even when DMs are properly unlearned before release, malicious finetuning can compromise this process, causing DMs to relearn the unlearned concepts. This occurs partly because certain benign concepts (e.g., "skin") retained in DMs are related to the unlearned ones (e.g., "nudity"), facilitating their relearning via finetuning. To address this, we propose meta-unlearning on DMs. Intuitively, a meta-unlearned DM should behave like an unlearned DM when used as is; moreover, if the meta-unlearned DM undergoes malicious finetuning on unlearned concepts, the related benign concepts retained within it will be triggered to self-destruct, hindering the relearning of unlearned concepts. Our meta-unlearning framework is compatible with most existing unlearning methods, requiring only the addition of an easy-to-implement meta objective. We validate our approach through empirical experiments on meta-unlearning concepts from Stable Diffusion models (SD-v1-4 and SDXL), supported by extensive ablation studies. Our code is available at https://github.com/sail-sg/Meta-Unlearning.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

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

  1. LU-500: A Logo Benchmark for Concept Unlearning

    cs.CV 2026-07 conditional novelty 6.0

    A new 500-company benchmark shows current concept-erasure methods cannot remove small logos from generated images without also changing unrelated content.

  2. Video Deepfake Abuse: How Company Choices Predictably Shape Misuse Patterns

    cs.CY 2025-11 conditional novelty 6.0

    A few open-weight video models and distribution platforms dominate the creation and spread of NSFW AI video, making developer and platform choices the main intervention points for reducing non-consensual deepfake abuse.

  3. Reason Before You Retrieve: Agentic Planning for Multi-modal RAG

    cs.AI 2026-06 reject novelty 5.0

    MM-R2 claims SOTA multimodal RAG accuracy on InfoSeek and Encyclopedic VQA via intent grounding plus a 10-topic KnowledgeMap, but its teacher trajectories leak the gold Wikipedia page and omit the image.

  4. CoreUnlearn: Rethinking Concept Unlearning through Disentangled Component-Level Erasure in Text-guided Diffusion Models

    cs.CR 2026-06 unverdicted novelty 4.0

    CoreUnlearn uses a Component Extraction Module and Swap Disentangling Strategy to remove only erasure-critical components from concept embeddings in diffusion models.