Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models

• URL: http://arxiv.org/abs/2503.09446v2
• Date: Tue, 18 Mar 2025 09:12:52 GMT
• Title: Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models
• Authors: Zhihua Tian, Sirun Nan, Ming Xu, Shengfang Zhai, Wenjie Qu, Jian Liu, Kui Ren, Ruoxi Jia, Jiaheng Zhang,
• Abstract summary: 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.
• Score: 24.15603438969762
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Text-to-image (T2I) diffusion models have achieved remarkable progress in generating high-quality images but also raise people's concerns about generating harmful or misleading content. While extensive approaches have been proposed to erase unwanted concepts without requiring retraining from scratch, they inadvertently degrade performance on normal generation tasks. In this work, we propose Interpret then Deactivate (ItD), a novel framework to enable precise concept removal in T2I diffusion models while preserving overall performance. ItD first employs a sparse autoencoder (SAE) to interpret each concept as a combination of multiple features. By permanently deactivating the specific features associated with target concepts, we repurpose SAE as a zero-shot classifier that identifies whether the input prompt includes target concepts, allowing selective concept erasure in diffusion models. Moreover, we demonstrate that ItD can be easily extended to erase multiple concepts without requiring further training. Comprehensive experiments across celebrity identities, artistic styles, and explicit content demonstrate ItD's effectiveness in eliminating targeted concepts without interfering with normal concept generation. Additionally, ItD is also robust against adversarial prompts designed to circumvent content filters. Code is available at: https://github.com/NANSirun/Interpret-then-deactivate.

Related papers

• ACE: Attentional Concept Erasure in Diffusion Models [0.0]
  Attentional Concept Erasure integrates a closed-form attention manipulation with lightweight fine-tuning. We show that ACE achieves state-of-the-art concept removal efficacy and robustness. 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. 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)
• Safe and Reliable Diffusion Models via Subspace Projection [27.65307410937119]
  We propose SAFER, a novel and efficient approach for thoroughly removing target concepts from T2I diffusion models. The method first identifies a concept-specific subspace $S_c$ associated with the target concept c. It then projects the prompt embeddings onto the subspace of $S_c$, effectively erasing the concept from the generated images.
  arXiv  Detail & Related papers  (2025-03-21T04:09:25Z)
• Concept Corrector: Erase concepts on the fly for text-to-image diffusion models [13.065682925662237]
  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)
• Concept Steerers: Leveraging K-Sparse Autoencoders for Controllable Generations [10.86252546314626]
  Text-to-image generative models are prone to adversarial attacks and inadvertently generate unsafe, unethical content.<n>We propose a novel framework leveraging k-sparse autoencoders (k-SAEs) to enable efficient and interpretable concept manipulation.<n>Our method yields an improvement of $mathbf20.01%$ in unsafe concept removal, is effective in style manipulation, and is $mathbfsim5$x faster than current state-of-the-art.
  arXiv  Detail & Related papers  (2025-01-31T11:52:47Z)
• SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders [4.013156524547073]
  Diffusion models can inadvertently generate harmful or undesirable content.<n>Recent machine unlearning approaches offer potential solutions but often lack transparency.<n>We introduce SAeUron, a novel method leveraging features learned by sparse autoencoders.
  arXiv  Detail & Related papers  (2025-01-29T23:29:47Z)
• DuMo: Dual Encoder Modulation Network for Precise Concept Erasure [75.05165577219425]
  We propose our Dual encoder Modulation network (DuMo) which achieves precise erasure of inappropriate target concepts with minimum impairment to non-target concepts.<n>Our method achieves state-of-the-art performance on Explicit Content Erasure, Cartoon Concept Removal and Artistic Style Erasure, clearly outperforming alternative methods.
  arXiv  Detail & Related papers  (2025-01-02T07:47:34Z)
• 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)
• Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models [58.74606272936636]
  Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. The models could be exploited for malicious purposes, such as generating images with violence or nudity, or creating unauthorized portraits of public figures in inappropriate contexts. concept removal methods have been proposed to modify diffusion models to prevent the generation of malicious and unwanted concepts.
  arXiv  Detail & Related papers  (2024-06-21T03:58:44Z)
• All but One: Surgical Concept Erasing with Model Preservation in Text-to-Image Diffusion Models [22.60023885544265]
  Large-scale datasets may contain sexually explicit, copyrighted, or undesirable content, which allows the model to directly generate them. Fine-tuning algorithms have been developed to tackle concept erasing in diffusion models. We present a new approach that solves all of these challenges.
  arXiv  Detail & Related papers  (2023-12-20T07:04:33Z)
• Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers [24.64639078273091]
  Concept erasure in text-to-image diffusion models aims to disable pre-trained diffusion models from generating images related to a target concept. We propose Reliable Concept Erasing via Lightweight Erasers (Receler)
  arXiv  Detail & Related papers  (2023-11-29T15:19:49Z)
• 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)
• Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models [79.50701155336198]
  textbfForget-Me-Not is designed to safely remove specified IDs, objects, or styles from a well-configured text-to-image model in as little as 30 seconds. We demonstrate that Forget-Me-Not can effectively eliminate targeted concepts while maintaining the model's performance on other concepts. It can also be adapted as a lightweight model patch for Stable Diffusion, allowing for concept manipulation and convenient distribution.
  arXiv  Detail & Related papers  (2023-03-30T17:58:11Z)

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.