{"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/salun-empowering-machine-unlearning-via","title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","arxiv_id":"2310.12508","date":"2023-10-19","proceeding":null,"authors":["Chongyu Fan","Jiancheng Liu","Yihua Zhang","Eric Wong","Dennis Wei","Sijia Liu"],"abstract":"With evolving data regulations, machine unlearning (MU) has become an important tool for fostering trust and safety in today's AI models. However, existing MU methods focusing on data and/or weight perspectives often suffer limitations in unlearning accuracy, stability, and cross-domain applicability. To address these challenges, we introduce the concept of 'weight saliency' for MU, drawing parallels with input saliency in model explanation. This innovation directs MU's attention toward specific model weights rather than the entire model, improving effectiveness and efficiency. The resultant method that we call saliency unlearning (SalUn) narrows the performance gap with 'exact' unlearning (model retraining from scratch after removing the forgetting data points). To the best of our knowledge, SalUn is the first principled MU approach that can effectively erase the influence of forgetting data, classes, or concepts in both image classification and generation tasks. As highlighted below, For example, SalUn yields a stability advantage in high-variance random data forgetting, e.g., with a 0.2% gap compared to exact unlearning on the CIFAR-10 dataset. Moreover, in preventing conditional diffusion models from generating harmful images, SalUn achieves nearly 100% unlearning accuracy, outperforming current state-of-the-art baselines like Erased Stable Diffusion and Forget-Me-Not. Codes are available at https://github.com/OPTML-Group/Unlearn-Saliency. (WARNING: This paper contains model outputs that may be offensive in nature.)","url_abs":"https://arxiv.org/abs/2310.12508v5","url_pdf":"https://arxiv.org/pdf/2310.12508v5.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":"salun-empowering-machine-unlearning-via","repo_url":"https://github.com/optml-group/unlearn-saliency","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"machine-unlearning","task_name":"Machine Unlearning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.12508","atlas_url":"https://app.syntology.ai/?focus=2310.12508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12508"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/optml-group/unlearn-saliency","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":11,"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":0,"samples":[{"code_sha256_prefix":"074c8fc7870f5cc9","entry":"FGSM_perturb","repo":"optml-group/unlearn-saliency","repo_kind":"official","path":"Classification/unlearn/boundary_sh.py","file_url":"https://github.com/optml-group/unlearn-saliency/blob/HEAD/Classification/unlearn/boundary_sh.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"074c8fc7870f5cc9"}},{"code_sha256_prefix":"20b8d1668895f8bb","entry":"discretize","repo":"optml-group/unlearn-saliency","repo_kind":"official","path":"Classification/unlearn/boundary_sh.py","file_url":"https://github.com/optml-group/unlearn-saliency/blob/HEAD/Classification/unlearn/boundary_sh.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"20b8d1668895f8bb"}},{"code_sha256_prefix":"3d980bf223d0e00b","entry":"fisher","repo":"optml-group/unlearn-saliency","repo_kind":"official","path":"Classification/unlearn/fisher.py","file_url":"https://github.com/optml-group/unlearn-saliency/blob/HEAD/Classification/unlearn/fisher.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d980bf223d0e00b"}},{"code_sha256_prefix":"c25079d6cf22a5e2","entry":"fisher_information_martix","repo":"optml-group/unlearn-saliency","repo_kind":"official","path":"Classification/unlearn/fisher.py","file_url":"https://github.com/optml-group/unlearn-saliency/blob/HEAD/Classification/unlearn/fisher.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c25079d6cf22a5e2"}},{"code_sha256_prefix":"aebe5de64c1725b4","entry":"get_require_grad_params","repo":"optml-group/unlearn-saliency","repo_kind":"official","path":"Classification/unlearn/Wfisher.py","file_url":"https://github.com/optml-group/unlearn-saliency/blob/HEAD/Classification/unlearn/Wfisher.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aebe5de64c1725b4"}},{"code_sha256_prefix":"cae29c9fba744465","entry":"l1_regularization","repo":"optml-group/unlearn-saliency","repo_kind":"official","path":"Classification/unlearn/FT.py","file_url":"https://github.com/optml-group/unlearn-saliency/blob/HEAD/Classification/unlearn/FT.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cae29c9fba744465"}},{"code_sha256_prefix":"4145035921358f67","entry":"sam_grad","repo":"optml-group/unlearn-saliency","repo_kind":"official","path":"Classification/unlearn/Wfisher.py","file_url":"https://github.com/optml-group/unlearn-saliency/blob/HEAD/Classification/unlearn/Wfisher.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4145035921358f67"}},{"code_sha256_prefix":"6fdded37bf329957","entry":"woodfisher","repo":"optml-group/unlearn-saliency","repo_kind":"official","path":"Classification/unlearn/Wfisher.py","file_url":"https://github.com/optml-group/unlearn-saliency/blob/HEAD/Classification/unlearn/Wfisher.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6fdded37bf329957"}},{"code_sha256_prefix":"1e7882ed2e1e9d82","entry":"GA","repo":"optml-group/unlearn-saliency","repo_kind":"official","path":"Classification/unlearn/GA_prune.py","file_url":"https://github.com/optml-group/unlearn-saliency/blob/HEAD/Classification/unlearn/GA_prune.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1e7882ed2e1e9d82"}},{"code_sha256_prefix":"552196cf57918ac6","entry":"GA","repo":"optml-group/unlearn-saliency","repo_kind":"official","path":"Classification/unlearn/GA_prune_bi.py","file_url":"https://github.com/optml-group/unlearn-saliency/blob/HEAD/Classification/unlearn/GA_prune_bi.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"552196cf57918ac6"}},{"code_sha256_prefix":"e953ece8832f74dd","entry":"get_mean_var","repo":"optml-group/unlearn-saliency","repo_kind":"official","path":"Classification/unlearn/fisher.py","file_url":"https://github.com/optml-group/unlearn-saliency/blob/HEAD/Classification/unlearn/fisher.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e953ece8832f74dd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}