{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/speed-scalable-precise-and-efficient-concept","title":"SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models","arxiv_id":"2503.07392","date":"2025-03-10","proceeding":null,"authors":["Ouxiang Li","YuAn Wang","Xinting Hu","Houcheng Jiang","Tao Liang","Yanbin Hao","Guojun Ma","Fuli Feng"],"abstract":"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. However, existing methods either require costly fine-tuning or degrade image quality for non-target concepts (i.e., prior) due to inherent optimization limitations. In this paper, we introduce SPEED, a model editing-based concept erasure approach that leverages null-space constraints for scalable, precise, and efficient erasure. Specifically, SPEED incorporates Influence-based Prior Filtering (IPF) to retain the most affected non-target concepts during erasing, Directed Prior Augmentation (DPA) to expand prior coverage while maintaining semantic consistency, and Invariant Equality Constraints (IEC) to regularize model editing by explicitly preserving key invariants during the T2I generation process. Extensive evaluations across multiple concept erasure tasks demonstrate that SPEED consistently outperforms existing methods in prior preservation while achieving efficient and high-fidelity concept erasure, successfully removing 100 concepts within just 5 seconds. Our code and models are available at: https://github.com/Ouxiang-Li/SPEED.","url_abs":"https://arxiv.org/abs/2503.07392v1","url_pdf":"https://arxiv.org/pdf/2503.07392v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"speed-scalable-precise-and-efficient-concept","repo_url":"https://github.com/ouxiang-li/speed","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"model-editing","task_name":"Model Editing"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.07392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07392"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ouxiang-li/speed","reach":null}],"summary":{"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f78e02400c7714c7","entry":"get_token_id","repo":"ouxiang-li/speed","repo_kind":"official","path":"train_erase_null.py","file_url":"https://github.com/ouxiang-li/speed/blob/HEAD/train_erase_null.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f78e02400c7714c7"}},{"code_sha256_prefix":"532023c2d7148124","entry":"edit_model","repo":"ouxiang-li/speed","repo_kind":"official","path":"train_erase_null.py","file_url":"https://github.com/ouxiang-li/speed/blob/HEAD/train_erase_null.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"532023c2d7148124"}},{"code_sha256_prefix":"deaf4e105eea11ad","entry":"generate_perturbed_embs","repo":"ouxiang-li/speed","repo_kind":"official","path":"train_erase_null.py","file_url":"https://github.com/ouxiang-li/speed/blob/HEAD/train_erase_null.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"deaf4e105eea11ad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}