{"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/generative-unlearning-for-any-identity","title":"Generative Unlearning for Any Identity","arxiv_id":"2405.09879","date":"2024-05-16","proceeding":"CVPR 2024 1","authors":["Juwon Seo","Sung-Hoon Lee","Tae-Young Lee","Seungjun Moon","Gyeong-Moon Park"],"abstract":"Recent advances in generative models trained on large-scale datasets have made it possible to synthesize high-quality samples across various domains. Moreover, the emergence of strong inversion networks enables not only a reconstruction of real-world images but also the modification of attributes through various editing methods. However, in certain domains related to privacy issues, e.g., human faces, advanced generative models along with strong inversion methods can lead to potential misuses. In this paper, we propose an essential yet under-explored task called generative identity unlearning, which steers the model not to generate an image of a specific identity. In the generative identity unlearning, we target the following objectives: (i) preventing the generation of images with a certain identity, and (ii) preserving the overall quality of the generative model. To satisfy these goals, we propose a novel framework, Generative Unlearning for Any Identity (GUIDE), which prevents the reconstruction of a specific identity by unlearning the generator with only a single image. GUIDE consists of two parts: (i) finding a target point for optimization that un-identifies the source latent code and (ii) novel loss functions that facilitate the unlearning procedure while less affecting the learned distribution. Our extensive experiments demonstrate that our proposed method achieves state-of-the-art performance in the generative machine unlearning task. The code is available at https://github.com/KHU-AGI/GUIDE.","url_abs":"https://arxiv.org/abs/2405.09879v1","url_pdf":"https://arxiv.org/pdf/2405.09879v1.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":"generative-unlearning-for-any-identity","repo_url":"https://github.com/khu-agi/guide","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-unlearning","task_name":"Machine Unlearning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.09879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.09879"}},"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/khu-agi/guide","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/KHU-AGI/GUIDE","reach":{"status":"ok"}}],"summary":{"ran":5,"ran_honours":1,"ran_draft_wrong":2,"unverified":5},"by_repo_kind":{"official":{"samples":13,"ran":8,"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":13,"samples":[{"code_sha256_prefix":"eef98780cbfa6ee7","entry":"FOV_to_intrinsics","repo":"KHU-AGI/GUIDE","repo_kind":"official","path":"camera_utils.py","file_url":"https://github.com/KHU-AGI/GUIDE/blob/HEAD/camera_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eef98780cbfa6ee7"}},{"code_sha256_prefix":"cd2592a84ba8679b","entry":"calculate_fid","repo":"KHU-AGI/GUIDE","repo_kind":"official","path":"evaluate_fid.py","file_url":"https://github.com/KHU-AGI/GUIDE/blob/HEAD/evaluate_fid.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cd2592a84ba8679b"}},{"code_sha256_prefix":"7f2564dfbc5014d9","entry":"extract_features","repo":"KHU-AGI/GUIDE","repo_kind":"official","path":"evaluate_fid.py","file_url":"https://github.com/KHU-AGI/GUIDE/blob/HEAD/evaluate_fid.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7f2564dfbc5014d9"}},{"code_sha256_prefix":"ad5dbf57f3ea2633","entry":"get_block","repo":"KHU-AGI/GUIDE","repo_kind":"official","path":"arcface.py","file_url":"https://github.com/KHU-AGI/GUIDE/blob/HEAD/arcface.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ad5dbf57f3ea2633"}},{"code_sha256_prefix":"ea7941eb1ea8ffb2","entry":"get_blocks","repo":"KHU-AGI/GUIDE","repo_kind":"official","path":"arcface.py","file_url":"https://github.com/KHU-AGI/GUIDE/blob/HEAD/arcface.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ea7941eb1ea8ffb2"}},{"code_sha256_prefix":"ae7700893d032177","entry":"image_to_tensor","repo":"KHU-AGI/GUIDE","repo_kind":"official","path":"unlearn.py","file_url":"https://github.com/KHU-AGI/GUIDE/blob/HEAD/unlearn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ae7700893d032177"}},{"code_sha256_prefix":"c54fea429589425d","entry":"l2_norm","repo":"KHU-AGI/GUIDE","repo_kind":"official","path":"arcface.py","file_url":"https://github.com/KHU-AGI/GUIDE/blob/HEAD/arcface.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c54fea429589425d"}},{"code_sha256_prefix":"fde42e3df1ce4605","entry":"tensor_to_image","repo":"KHU-AGI/GUIDE","repo_kind":"official","path":"unlearn.py","file_url":"https://github.com/KHU-AGI/GUIDE/blob/HEAD/unlearn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fde42e3df1ce4605"}},{"code_sha256_prefix":"9d31d2c4cd16bb2d","entry":"ask_yes_no","repo":"KHU-AGI/GUIDE","repo_kind":"official","path":"dnnlib/util.py","file_url":"https://github.com/KHU-AGI/GUIDE/blob/HEAD/dnnlib/util.py","link_basis":"harvester_set","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":"9d31d2c4cd16bb2d"}},{"code_sha256_prefix":"93b8fbfaaf3d24e6","entry":"calculate_statistics","repo":"KHU-AGI/GUIDE","repo_kind":"official","path":"evaluate_fid.py","file_url":"https://github.com/KHU-AGI/GUIDE/blob/HEAD/evaluate_fid.py","link_basis":"harvester_set","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":"93b8fbfaaf3d24e6"}},{"code_sha256_prefix":"053fc534bc6bb989","entry":"format_time","repo":"KHU-AGI/GUIDE","repo_kind":"official","path":"dnnlib/util.py","file_url":"https://github.com/KHU-AGI/GUIDE/blob/HEAD/dnnlib/util.py","link_basis":"harvester_set","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":"053fc534bc6bb989"}},{"code_sha256_prefix":"77f4aa0649e7f404","entry":"format_time_brief","repo":"KHU-AGI/GUIDE","repo_kind":"official","path":"dnnlib/util.py","file_url":"https://github.com/KHU-AGI/GUIDE/blob/HEAD/dnnlib/util.py","link_basis":"harvester_set","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":"77f4aa0649e7f404"}},{"code_sha256_prefix":"4e274bc76c65b5f5","entry":"update_config","repo":"KHU-AGI/GUIDE","repo_kind":"official","path":"goae/swin_config.py","file_url":"https://github.com/KHU-AGI/GUIDE/blob/HEAD/goae/swin_config.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":"4e274bc76c65b5f5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}