Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration

• URL: http://arxiv.org/abs/2604.15829v1
• Date: Fri, 17 Apr 2026 08:32:39 GMT
• Title: Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration
• Abstract summary: Text-to-image generative models can inadvertently produce unsafe or undesirable content due to implicit biases embedded in large-scale training datasets.<n>We propose TICoE, a text-image Collaborative Erasing framework that achieves precise and faithful concept removal.
• Score: 31.335104022933695
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-image generative models have achieved impressive fidelity and diversity, but can inadvertently produce unsafe or undesirable content due to implicit biases embedded in large-scale training datasets. Existing concept erasure methods, whether text-only or image-assisted, face trade-offs: textual approaches often fail to fully suppress concepts, while naive image-guided methods risk over-erasing unrelated content. We propose TICoE, a text-image Collaborative Erasing framework that achieves precise and faithful concept removal through a continuous convex concept manifold and hierarchical visual representation learning. TICoE precisely removes target concepts while preserving unrelated semantic and visual content. To objectively assess the quality of erasure, we further introduce a fidelity-oriented evaluation strategy that measures post-erasure usability. Experiments on multiple benchmarks show that TICoE surpasses prior methods in concept removal precision and content fidelity, enabling safer, more controllable text-to-image generation. Our code is available at https://github.com/OpenAscent-L/TICoE.git

Related papers

• ForceForget: Reinforcement Concept Removal for Enhancing Safety in Text-to-Image Models [10.644460694822467]
  With the advance of generative AI, the text-to-image (T2I) model has the ability to generate various contents.<n>This paper focuses on eliminating unsafe content while maintaining model capability in safe semantic meaning interpretation.<n>We introduce the Safe Adapter to project partial text embedding for efficient concept regulation in cross-attention layers.
  arXiv  Detail & Related papers  (2026-06-12T11:12:33Z)
• VCE: Safe Autoregressive Image Generation via Visual Contrast Exploitation [57.36681904639463]
  Methods to safeguard autoregressive text-to-image models remain underexplored.<n>We propose Visual Contrast Exploitation (VCE), a novel framework that precisely decouples unsafe concepts from their associated content semantics.<n>Our experiments demonstrate that our method effectively secures the model, achieving state-of-the-art results while erasing unsafe concepts and maintaining the integrity of unrelated safe concepts.
  arXiv  Detail & Related papers  (2025-09-21T09:00:27Z)
• 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)
• CRCE: Coreference-Retention Concept Erasure in Text-to-Image Diffusion Models [19.205261933636645]
  We introduce CRCE, a novel concept erasure framework.<n>By explicitly modelling coreferential and retained concepts semantically, CRCE enables more precise concept removal.<n>Experiments demonstrate that CRCE outperforms existing methods on diverse erasure tasks.
  arXiv  Detail & Related papers  (2025-03-18T13:09:01Z)
• 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 Corrector: Erase concepts on the fly for text-to-image diffusion models [38.99973711993937]
  Concept erasure aims to erase any undesired concepts that the models can generate.<n>We propose Concept Corrector, which checks target concepts based on visual features provided by final generated images predicted at certain time steps.<n>In the whole pipeline, our method changes no model parameters and only requires a given target concept as well as the corresponding replacement content.
  arXiv  Detail & Related papers  (2025-02-22T21:53:43Z)
• Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction [88.18235230849554]
  Training multimodal generative models on large, uncurated datasets can result in users being exposed to harmful, unsafe and controversial or culturally-inappropriate outputs.<n>We leverage safe embeddings and a modified diffusion process with weighted tunable summation in the latent space to generate safer images.<n>We identify trade-offs between safety and censorship, which presents a necessary perspective in the development of ethical AI models.
  arXiv  Detail & Related papers  (2024-11-21T09:47:13Z)
• Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion [51.931083971448885]
  We propose a framework named Human Feedback Inversion (HFI), where human feedback on model-generated images is condensed into textual tokens guiding the mitigation or removal of problematic images. Our experimental results demonstrate our framework significantly reduces objectionable content generation while preserving image quality, contributing to the ethical deployment of AI in the public sphere.
  arXiv  Detail & Related papers  (2024-07-17T05:21:41Z)
• 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.