Pith. sign in

REVIEW 7 cited by

Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation

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 2410.15618 v4 pith:EIE2VBL3 submitted 2024-10-21 cs.LG cs.CV

classification cs.LGcs.CV
keywords conceptscontentdiffusionmodeladversarialchangeserasureimpact
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Diffusion models excel at generating visually striking content from text but can inadvertently produce undesirable or harmful content when trained on unfiltered internet data. A practical solution is to selectively removing target concepts from the model, but this may impact the remaining concepts. Prior approaches have tried to balance this by introducing a loss term to preserve neutral content or a regularization term to minimize changes in the model parameters, yet resolving this trade-off remains challenging. In this work, we propose to identify and preserving concepts most affected by parameter changes, termed as \textit{adversarial concepts}. This approach ensures stable erasure with minimal impact on the other concepts. We demonstrate the effectiveness of our method using the Stable Diffusion model, showing that it outperforms state-of-the-art erasure methods in eliminating unwanted content while maintaining the integrity of other unrelated elements. Our code is available at https://github.com/tuananhbui89/Erasing-Adversarial-Preservation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate

    cs.LG 2026-07 conditional novelty 7.0 of 10

    Cross-attention maps serve as a tractable surrogate for manifold proximity, enabling automatic synthesis of anchors that suppress normal-space drift in diffusion unlearning.

  2. SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models

    cs.CV 2025-09 conditional novelty 7.0 of 10

    SuMa erases narrow concepts from text-to-image models by mapping the concept's token subspace onto a nearby reference subspace, achieving robustness against adversarial attacks with image quality close to standard era...

  3. Semantic Steering for Controllable Generation: Tuning-Free Concept Erasure in Multimodal Diffusion Transformers

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A single steering vector extracted from the middle text layer of a multimodal diffusion transformer can erase concepts like nudity, celebrities, and art styles at inference time, with no training.

  4. Erase but Preserve: Controllable Removal of Copyrighted Animation Characters via Optimized Semantic Anchors

    cs.CV 2026-08 conditional novelty 6.0 of 10

    Optimized continuous embedding anchors with structure-aware adaptive replacement erase copyrighted animation characters from text-to-image diffusion outputs while preserving image context.

  5. A Unified Framework for Diffusion Model Unlearning with f-Divergence

    cs.LG 2025-09 conditional novelty 6.0 of 10

    Diffusion model unlearning is generalized from KL/MSE to any f-divergence, with closed-form Hellinger and chi-square losses and a variational min-max form.

  6. Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts

    cs.CV 2025-04 conditional novelty 6.0 of 10

    ANT erases unwanted concepts from text-to-image diffusion models by reversing the guidance direction only during mid-to-late denoising, preserving early structural quality.

  7. TRACE: Trajectory-Constrained Concept Erasure in Diffusion Models

    cs.CV 2025-05 reject novelty 2.0 of 10

    TRACE combines a closed-form cross-attention nullification with a late-timestep fine-tuning loss to erase concepts from diffusion models, claiming better erasure and fidelity than published baselines.

Pith tools