Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models

• URL: http://arxiv.org/abs/2605.25765v1
• Date: Mon, 25 May 2026 12:18:47 GMT
• Title: Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models
• Abstract summary: Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining.<n>Existing closed-form methods represent the target concept through the text encoder's response to a few short anchor prompts that name it.<n>We propose PURE, a closed-form method that builds the forget and retain bases from per-layer cross-attention activations.
• Score: 6.701045531467819
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining. Closed-form methods are attractive in this setting because they apply a single deterministic edit to the cross-attention weights and add no inference-time cost. Existing closed-form methods, however, represent the target concept through the text encoder's response to a few short anchor prompts that name it, and paraphrased prompts that evoke the concept without naming it consistently bypass the edit. We argue that the target should instead be represented in the cross-attention activation space. Text embeddings describe the user's prompt, while cross-attention activations describe what the model is about to render, and the latter generalize to paraphrase the anchor templates do not cover. Building on this observation, we propose PURE (Projection in U-Net Rendering for Erasure), a closed-form method that builds the forget and retain bases from per-layer cross-attention activations captured along a short denoising trajectory and applies a single linear projector to the cross-attention key and value weights. On a recent holistic concept-unlearning benchmark covering ten concepts across artistic style, intellectual property, celebrity, and NSFW categories, PURE significantly reduces target leakage under paraphrased and adversarial prompts while preserving retain concepts close to the unedited model, yielding the best overall forget-retain trade-off among evaluated methods.

Related papers

• Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models [105.53190946111586]
  We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
  arXiv  Detail & Related papers  (2026-09-09T09:07:40Z)
• Erasing Without Collateral Damage: Precise Concept Removal in Diffusion Models [10.269961654607108]
  Training-free concept erasure is attractive mechanism for controlling text-to-image diffusion models.<n>But precise erasure often comes at the cost of damaging semantically related non-target concepts.<n>We introduce CARE, a closed-form concept erasure operator that replaces the raw target direction with a kept-subspace-aware direction.
  arXiv  Detail & Related papers  (2026-07-06T16:21:09Z)
• Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition [81.2779530670268]
  Vision-Language Models (VLMs) have significantly advanced zero-shot image recognition.<n>This paper enhances prompt by incorporating class-specific concepts.<n>Our method consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-03-09T03:11:11Z)
• ConceptPrism: Concept Disentanglement in Personalized Diffusion Models via Residual Token Optimization [11.472088067393074]
  ConceptPrism is a novel framework that automatically disentangles the shared visual concept from image-specific residuals.<n>In experiments, ConceptPrism effectively resolves concept entanglement, achieving a significantly improved trade-off between fidelity and alignment.
  arXiv  Detail & Related papers  (2026-02-23T07:46:19Z)
• Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gate [10.996274286143244]
  Concept erasing has been investigated with the goals of deleting target concepts in diffusion models while preserving other concepts with minimal distortion.<n>We propose a novel framework, dubbed Concept Pinpoint Eraser (CPE), by adding emphnonlinear Residual Attention Gates (ResAGs) that selectively erase (or cut) target concepts.<n>CPE outperforms prior arts by keeping diverse remaining concepts while deleting the target concepts with robustness against attack prompts.
  arXiv  Detail & Related papers  (2025-06-28T08:17:19Z)
• ACE: Attentional Concept Erasure in Diffusion Models [0.0]
  Attentional Concept Erasure integrates a closed-form attention manipulation with lightweight fine-tuning.<n>We show that ACE achieves state-of-the-art concept removal efficacy and robustness.<n>Compared to prior methods, ACE better balances generality (erasing concept and related terms) and specificity (preserving unrelated content)
  arXiv  Detail & Related papers  (2025-04-16T08:16:28Z)
• Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models [56.35484513848296]
  FADE (Fine grained Attenuation for Diffusion Erasure) is an adjacency-aware unlearning algorithm for text-to-image generative models.<n>It removes target concepts with minimal impact on correlated concepts, achieving a 12% improvement in retention performance over state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-25T15:49:48Z)
• Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models [17.694838443796026]
  Interpret then Deactivate (ItD) is a novel framework to enable precise concept removal in T2I diffusion models.<n>ItD uses a sparse autoencoder to interpret each concept as a combination of multiple features.<n>It can be easily extended to erase multiple concepts without requiring further training.
  arXiv  Detail & Related papers  (2025-03-12T14:46:40Z)
• TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models [53.937498564603054]
  Recent advances in text-to-image diffusion models enable photorealistic image generation, but they also risk producing malicious content, such as NSFW images.<n>To mitigate risk, concept erasure methods are studied to facilitate the model to unlearn specific concepts.<n>We propose TRCE, using a two-stage concept erasure strategy to achieve an effective trade-off between reliable erasure and knowledge preservation.
  arXiv  Detail & Related papers  (2025-03-10T14:37:53Z)
• Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision Localization [48.20360860166279]
  Large-scale diffusion models produce high-quality images but often generate unwanted content, such as sexually explicit or violent content.<n>We propose a novel approach for targeted concept replacing in diffusion models, enabling specific concepts to be removed without affecting non-target areas.<n>Our method introduces a dedicated concept localizer for precisely identifying the target concept during the denoising process, trained with few-shot learning to require minimal labeled data.<n>Within the identified region, we introduce a training-free Dual Prompts Cross-Attention (DPCA) module to substitute the target concept, ensuring minimal disruption to surrounding content.
  arXiv  Detail & Related papers  (2024-12-02T08:05:39Z)
• Implicit Concept Removal of Diffusion Models [92.55152501707995]
  Text-to-image (T2I) diffusion models often inadvertently generate unwanted concepts such as watermarks and unsafe images. We present the Geom-Erasing, a novel concept removal method based on the geometric-driven control.
  arXiv  Detail & Related papers  (2023-10-09T17:13:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.