SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models
This work addresses a critical need for scalable and high-fidelity concept removal in diffusion models, which is important for developers and users concerned with ethical AI deployment, though it is incremental as it builds on existing model editing techniques.
The paper tackles the problem of efficiently and precisely erasing multiple target concepts from text-to-image diffusion models to address copyright, offensive content, and privacy issues, achieving the erasure of 100 concepts within only 5 seconds while outperforming existing methods in preserving non-target concepts.
Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, offensive content, and privacy violations. In scalable applications, fine-tuning-based methods are time-consuming to precisely erase multiple target concepts, while real-time editing-based methods often degrade the generation quality of non-target concepts due to conflicting optimization objectives. To address this dilemma, we introduce SPEED, an efficient concept erasure approach that directly edits model parameters. SPEED searches for a null space, a model editing space where parameter updates do not affect non-target concepts, to achieve scalable and precise erasure. To facilitate accurate null space optimization, we incorporate three complementary strategies: Influence-based Prior Filtering (IPF) to selectively retain the most affected non-target concepts, Directed Prior Augmentation (DPA) to enrich the filtered retain set with semantically consistent variations, and Invariant Equality Constraints (IEC) to preserve key invariants during the T2I generation process. Extensive evaluations across multiple concept erasure tasks demonstrate that SPEED consistently outperforms existing methods in non-target preservation while achieving efficient and high-fidelity concept erasure, successfully erasing 100 concepts within only 5 seconds. Our code and models are available at: https://github.com/Ouxiang-Li/SPEED.