{"slug": "orthogonal-concept-erasure-for-diffusion-models", "title": "Orthogonal Concept Erasure for Diffusion Models", "summary": "Researchers have developed Orthogonal Concept Erasure (OCE), a new method for diffusion models that removes unwanted content while preserving overall image generation quality. The technique uses multiplicative parameter updates through orthogonal transformations, enabling precise concept erasure without the computational costs of training-based approaches. OCE can erase up to 100 concepts in 4.3 seconds, outperforming existing methods in both single- and multi-concept erasure tasks.", "body_md": "arXiv:2605.28902v1 Announce Type: new\nAbstract: Concept erasure has emerged as a promising approach to mitigate undesired or unsafe content in diffusion models, yet existing methods still face significant limitations. While training-based methods are effective, their high computational cost limits scalability. Editing-based methods are more efficient and deployment-friendly, yet they struggle to simultaneously achieve precise concept erasure and preserve overall generative capacity. We identify this core limitation of the editing-based methods as reliance on additive parameter updates. Our empirical analysis reveals that concept semantics primarily depend on neuron direction rather than neuron magnitude, while overall generative capacity relies on the angular geometry of neurons. As additive updates inherently entangle direction, magnitude, and angular geometry, they inevitably introduce unintended interference between concept erasure and overall generation performance. To address this, we propose Orthogonal Concept Erasure (OCE), which reformulates editing-based erasure as multiplicative parameter updates from a geometric perspective. Specifically, OCE applies layer-wise orthogonal transformations derived from a closed-form solution to the parameters, enabling precise concept erasure while preserving the neuron magnitude and angular geometry. Furthermore, to address conflicting constraints in multi-concept erasure, OCE introduces a subspace-level objective with structured subspace manipulation, yielding a more effective and scalable erasure. Extensive experiments on single- and multi-concept erasure demonstrate that OCE outperforms existing methods in concept erasure and non-target preservation, erasing up to 100 concepts in 4.3 s. Code: https://github.com/HansSunY/OCE.", "url": "https://wpnews.pro/news/orthogonal-concept-erasure-for-diffusion-models", "canonical_source": "https://arxiv.org/abs/2605.28902", "published_at": "2026-05-29 04:00:00+00:00", "updated_at": "2026-05-29 04:20:38.286040+00:00", "lang": "en", "topics": ["generative-ai", "ai-safety", "machine-learning", "neural-networks", "ai-research"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/orthogonal-concept-erasure-for-diffusion-models", "markdown": "https://wpnews.pro/news/orthogonal-concept-erasure-for-diffusion-models.md", "text": "https://wpnews.pro/news/orthogonal-concept-erasure-for-diffusion-models.txt", "jsonld": "https://wpnews.pro/news/orthogonal-concept-erasure-for-diffusion-models.jsonld"}}