{"ID":2865928,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21008","arxiv_id":"2509.21008","title":"A Single Neuron Works: Precise Concept Erasure in Text-to-Image Diffusion Models","abstract":"Text-to-image models exhibit remarkable capabilities in image generation. However, they also pose safety risks of generating harmful content. A key challenge of existing concept erasure methods is the precise removal of target concepts while minimizing degradation of image quality. In this paper, we propose Single Neuron-based Concept Erasure (SNCE), a novel approach that can precisely prevent harmful content generation by manipulating only a single neuron. Specifically, we train a Sparse Autoencoder (SAE) to map text embeddings into a sparse, disentangled latent space, where individual neurons align tightly with atomic semantic concepts. To accurately locate neurons responsible for harmful concepts, we design a novel neuron identification method based on the modulated frequency scoring of activation patterns. By suppressing activations of the harmful concept-specific neuron, SNCE achieves surgical precision in concept erasure with minimal disruption to image quality. Experiments on various benchmarks demonstrate that SNCE achieves state-of-the-art results in target concept erasure, while preserving the model's generation capabilities for non-target concepts. Additionally, our method exhibits strong robustness against adversarial attacks, significantly outperforming existing methods.","short_abstract":"Text-to-image models exhibit remarkable capabilities in image generation. However, they also pose safety risks of generating harmful content. A key challenge of existing concept erasure methods is the precise removal of target concepts while minimizing degradation of image quality. In this paper, we propose Single Neur...","url_abs":"https://arxiv.org/abs/2509.21008","url_pdf":"https://arxiv.org/pdf/2509.21008v1","authors":"[\"Qinqin He\",\"Jiaqi Weng\",\"Jialing Tao\",\"Hui Xue\"]","published":"2025-09-25T11:10:33Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}