{"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/towards-safe-self-distillation-of-internet","title":"Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models","arxiv_id":"2307.05977","date":"2023-07-12","proceeding":null,"authors":["Sanghyun Kim","Seohyeon Jung","Balhae Kim","Moonseok Choi","Jinwoo Shin","Juho Lee"],"abstract":"Large-scale image generation models, with impressive quality made possible by the vast amount of data available on the Internet, raise social concerns that these models may generate harmful or copyrighted content. The biases and harmfulness arise throughout the entire training process and are hard to completely remove, which have become significant hurdles to the safe deployment of these models. In this paper, we propose a method called SDD to prevent problematic content generation in text-to-image diffusion models. We self-distill the diffusion model to guide the noise estimate conditioned on the target removal concept to match the unconditional one. Compared to the previous methods, our method eliminates a much greater proportion of harmful content from the generated images without degrading the overall image quality. Furthermore, our method allows the removal of multiple concepts at once, whereas previous works are limited to removing a single concept at a time.","url_abs":"https://arxiv.org/abs/2307.05977v1","url_pdf":"https://arxiv.org/pdf/2307.05977v1.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":"towards-safe-self-distillation-of-internet","repo_url":"https://github.com/nannullna/safe-diffusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.05977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.05977"}},"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":"deterministic:regex_extraction","url":"https://github.com/ml-research/Q16","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nannullna/safe-diffusion","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"found_in_text":{"samples":1,"ran":0,"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":1,"samples":[{"code_sha256_prefix":"9f927d43843c43af","entry":"load_prompts","repo":"nannullna/safe-diffusion","repo_kind":"official","path":"generate.py","file_url":"https://github.com/nannullna/safe-diffusion/blob/HEAD/generate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f927d43843c43af"}},{"code_sha256_prefix":"26275c4c2014b979","entry":"prepare_extra_step_kwargs","repo":"nannullna/safe-diffusion","repo_kind":"official","path":"train_sdd.py","file_url":"https://github.com/nannullna/safe-diffusion/blob/HEAD/train_sdd.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"26275c4c2014b979"}},{"code_sha256_prefix":"d94d955dcf0da562","entry":"ClipSimModel","repo":"ml-research/Q16","repo_kind":"found_in_text","path":"main/models/clip.py","file_url":"https://github.com/ml-research/Q16/blob/HEAD/main/models/clip.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d94d955dcf0da562"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}