Localized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation Misdirection

• URL: http://arxiv.org/abs/2602.19631v1
• Date: Mon, 23 Feb 2026 09:18:27 GMT
• Title: Localized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation Misdirection
• Abstract summary: We propose High-Level Representation Misdirection (HiRM), which misdirects high-level semantic representations in the text encoder toward designated vectors.<n>Our strategy enables precise concept removal with minimal impact on unrelated concepts.<n>HiRM also preserves generative utility at low training cost, transfers to state-of-the-art architectures such as Flux without additional training, and shows synergistic effects with denoiser-based concept erasing methods.
• Score: 7.863370847022858
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in text-to-image (T2I) diffusion models have seen rapid and widespread adoption. However, their powerful generative capabilities raise concerns about potential misuse for synthesizing harmful, private, or copyrighted content. To mitigate such risks, concept erasure techniques have emerged as a promising solution. Prior works have primarily focused on fine-tuning the denoising component (e.g., the U-Net backbone). However, recent causal tracing studies suggest that visual attribute information is localized in the early self-attention layers of the text encoder, indicating a potential alternative for concept erasing. Building on this insight, we conduct preliminary experiments and find that directly fine-tuning early layers can suppress target concepts but often degrades the generation quality of non-target concepts. To overcome this limitation, we propose High-Level Representation Misdirection (HiRM), which misdirects high-level semantic representations of target concepts in the text encoder toward designated vectors such as random directions or semantically defined directions (e.g., supercategories), while updating only early layers that contain causal states of visual attributes. Our decoupling strategy enables precise concept removal with minimal impact on unrelated concepts, as demonstrated by strong results on UnlearnCanvas and NSFW benchmarks across diverse targets (e.g., objects, styles, nudity). HiRM also preserves generative utility at low training cost, transfers to state-of-the-art architectures such as Flux without additional training, and shows synergistic effects with denoiser-based concept erasing 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)
• EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders [103.46709005379591]
  Concept erasure offers a principled remedy by removing unwanted semantics from pretrained models.<n>Existing approaches typically operate at a coarse quality, misaligned with the finegrained, distributed nature of concept representations.<n>We propose EraseSAE, a novel framework that leverages sparse autoencoders to achieve surgical concept erasure.
  arXiv  Detail & Related papers  (2026-09-03T10:23:37Z)
• Uni-AdaVD: Universal Concept Erasure for Visual Generation via Orthogonal Value Decomposition [62.947473058878565]
  We present Uni-AdaVD, a universal inference-time concept erasure framework for visual generation.<n>Our results suggest that Uni-AdaVD provides an efficient and adaptable safety mechanism for modern visual generative models.
  arXiv  Detail & Related papers  (2026-07-16T03:16:51Z)
• Whispers in the Noise: Surrogate-Guided Concept Awakening via a Multi-Agent Framework [10.018906972154218]
  Concept erasure aims to mitigate risks by removing specific concepts from pretrained models.<n>Recent studies show that such methods often suppress rather than fully eliminate target concepts, leaving models vulnerable to awakening attacks.<n>We propose ConceptAgent, a training-free, black-box, multi-agent framework that awakens erased concepts by initializing the denoising trajectory from surrogate-guided noisy states.
  arXiv  Detail & Related papers  (2026-05-18T09:55:36Z)
• Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models [49.10620605347065]
  We propose Differential Vector Erasure (DVE), a training-free concept erasure method specifically designed for flow matching models.<n>Our key insight is that semantic concepts are implicitly encoded in the directional structure of the velocity field governing the generative flow.<n>During inference, DVE selectively removes concept-specific components by projecting the velocity field onto the differential direction, enabling precise concept suppression without affecting irrelevant semantics.
  arXiv  Detail & Related papers  (2026-02-01T08:05:45Z)
• AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models [63.05306474002547]
  Regulatory frameworks mandating the 'right to be forgotten' drive the need for machine unlearning.<n>We introduce AUVIC, a novel visual concept unlearning framework for MLLMs.<n>We show that AUVIC achieves state-of-the-art target forgetting rates while incurs minimal performance degradation on non-target concepts.
  arXiv  Detail & Related papers  (2025-11-14T13:35:32Z)
• 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)
• TRACE: Trajectory-Constrained Concept Erasure in Diffusion Models [0.0]
  Concept erasure aims to remove or suppress specific concept information in a generative model.<n>Trajectory-Constrained Attentional Concept Erasure (TRACE) is a novel method to erase targeted concepts from diffusion models.<n>TRACE achieves state-of-the-art performance, outperforming recent methods such as ANT, EraseAnything, and MACE in terms of removal efficacy and output quality.
  arXiv  Detail & Related papers  (2025-05-29T10:15:22Z)
• Erased or Dormant? Rethinking Concept Erasure Through Reversibility [6.895055915600732]
  We evaluate two representative concept erasure methods, Unified Concept Editing and Erased Stable Diffusion.<n>We show that erased concepts often reemerge with substantial visual fidelity after minimal adaptation.<n>Our findings reveal critical limitations in existing concept erasure approaches.
  arXiv  Detail & Related papers  (2025-05-22T03:26:46Z)
• One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework [127.07102988701092]
  We introduce the first text-image Collaborative Concept Erasing (Co-Erasing) framework.<n>Co-Erasing describes the concept jointly by text prompts and the corresponding undesirable images induced by the prompts.<n>We design a text-guided image concept refinement strategy that directs the model to focus on visual features most relevant to the specified text concept.
  arXiv  Detail & Related papers  (2025-05-16T11:25:50Z)
• 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)
• 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)
• Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models [76.39651111467832]
  We introduce Reliable and Efficient Concept Erasure (RECE), a novel approach that modifies the model in 3 seconds without necessitating additional fine-tuning. To mitigate inappropriate content potentially represented by derived embeddings, RECE aligns them with harmless concepts in cross-attention layers. The derivation and erasure of new representation embeddings are conducted iteratively to achieve a thorough erasure of inappropriate concepts.
  arXiv  Detail & Related papers  (2024-07-17T08:04:28Z)
• Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient [20.698305103879232]
  We propose a novel concept domain correction framework named textbfDoCo (textbfDomaintextbfCorrection)<n>By aligning the output domains of sensitive and anchor concepts through adversarial training, our approach ensures comprehensive unlearning of target concepts.<n>We also introduce a concept-preserving gradient surgery technique that mitigates conflicting gradient components, thereby preserving the model's utility while unlearning specific concepts.
  arXiv  Detail & Related papers  (2024-05-24T07:47:36Z)
• 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.