{"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/geometry-aware-instance-reweighted-1","title":"Geometry-aware Instance-reweighted Adversarial Training","arxiv_id":"2010.01736","date":"2020-10-05","proceeding":"ICLR 2021 1","authors":["Jingfeng Zhang","Jianing Zhu","Gang Niu","Bo Han","Masashi Sugiyama","Mohan Kankanhalli"],"abstract":"In adversarial machine learning, there was a common belief that robustness and accuracy hurt each other. The belief was challenged by recent studies where we can maintain the robustness and improve the accuracy. However, the other direction, whether we can keep the accuracy while improving the robustness, is conceptually and practically more interesting, since robust accuracy should be lower than standard accuracy for any model. In this paper, we show this direction is also promising. Firstly, we find even over-parameterized deep networks may still have insufficient model capacity, because adversarial training has an overwhelming smoothing effect. Secondly, given limited model capacity, we argue adversarial data should have unequal importance: geometrically speaking, a natural data point closer to/farther from the class boundary is less/more robust, and the corresponding adversarial data point should be assigned with larger/smaller weight. Finally, to implement the idea, we propose geometry-aware instance-reweighted adversarial training, where the weights are based on how difficult it is to attack a natural data point. Experiments show that our proposal boosts the robustness of standard adversarial training; combining two directions, we improve both robustness and accuracy of standard adversarial training.","url_abs":"https://arxiv.org/abs/2010.01736v2","url_pdf":"https://arxiv.org/pdf/2010.01736v2.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":"geometry-aware-instance-reweighted-1","repo_url":"https://github.com/fanghenshaometeor/diversity-via-orthogonality","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"geometry-aware-instance-reweighted-1","repo_url":"https://github.com/zjfheart/Geometry-aware-Instance-reweighted-Adversarial-Training","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.01736","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01736"}},"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/zjfheart/Geometry-aware-Instance-reweighted-Adversarial-Training","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fanghenshaometeor/diversity-via-orthogonality","reach":null}],"summary":{"ran_fixture":1,"ran_draft_wrong":2,"ran":1},"by_repo_kind":{"listed":{"samples":4,"ran":4,"repositories":2}},"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":4,"samples":[{"code_sha256_prefix":"1876ed1e7b185aba","entry":"GAIR_trades_loss","repo":"zjfheart/Geometry-aware-Instance-reweighted-Adversarial-Training","repo_kind":"listed","path":"GAIR_RST/losses.py","file_url":"https://github.com/zjfheart/Geometry-aware-Instance-reweighted-Adversarial-Training/blob/HEAD/GAIR_RST/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1876ed1e7b185aba"}},{"code_sha256_prefix":"044ec38c1bb631ec","entry":"entropy_loss","repo":"zjfheart/Geometry-aware-Instance-reweighted-Adversarial-Training","repo_kind":"listed","path":"GAIR_RST/losses.py","file_url":"https://github.com/zjfheart/Geometry-aware-Instance-reweighted-Adversarial-Training/blob/HEAD/GAIR_RST/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"044ec38c1bb631ec"}},{"code_sha256_prefix":"560d41c0d04aee9c","entry":"pgd_generate","repo":"zjfheart/Geometry-aware-Instance-reweighted-Adversarial-Training","repo_kind":"listed","path":"GAIR_RST/losses.py","file_url":"https://github.com/zjfheart/Geometry-aware-Instance-reweighted-Adversarial-Training/blob/HEAD/GAIR_RST/losses.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":"560d41c0d04aee9c"}},{"code_sha256_prefix":"b5fd8ea9af3f8855","entry":"trades_dio_loss","repo":"fanghenshaometeor/diversity-via-orthogonality","repo_kind":"listed","path":"DIO+TRADES/trades.py","file_url":"https://github.com/fanghenshaometeor/diversity-via-orthogonality/blob/HEAD/DIO%2BTRADES/trades.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b5fd8ea9af3f8855"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}