{"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/revisiting-adversarial-training-under-long","title":"Revisiting Adversarial Training under Long-Tailed Distributions","arxiv_id":"2403.10073","date":"2024-03-15","proceeding":"CVPR 2024 1","authors":["Xinli Yue","Ningping Mou","Qian Wang","Lingchen Zhao"],"abstract":"Deep neural networks are vulnerable to adversarial attacks, often leading to erroneous outputs. Adversarial training has been recognized as one of the most effective methods to counter such attacks. However, existing adversarial training techniques have predominantly been tested on balanced datasets, whereas real-world data often exhibit a long-tailed distribution, casting doubt on the efficacy of these methods in practical scenarios. In this paper, we delve into adversarial training under long-tailed distributions. Through an analysis of the previous work \"RoBal\", we discover that utilizing Balanced Softmax Loss alone can achieve performance comparable to the complete RoBal approach while significantly reducing training overheads. Additionally, we reveal that, similar to uniform distributions, adversarial training under long-tailed distributions also suffers from robust overfitting. To address this, we explore data augmentation as a solution and unexpectedly discover that, unlike results obtained with balanced data, data augmentation not only effectively alleviates robust overfitting but also significantly improves robustness. We further investigate the reasons behind the improvement of robustness through data augmentation and identify that it is attributable to the increased diversity of examples. Extensive experiments further corroborate that data augmentation alone can significantly improve robustness. Finally, building on these findings, we demonstrate that compared to RoBal, the combination of BSL and data augmentation leads to a +6.66% improvement in model robustness under AutoAttack on CIFAR-10-LT. Our code is available at https://github.com/NISPLab/AT-BSL .","url_abs":"https://arxiv.org/abs/2403.10073v1","url_pdf":"https://arxiv.org/pdf/2403.10073v1.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":"revisiting-adversarial-training-under-long","repo_url":"https://github.com/nisplab/at-bsl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"adversarial-defense","task_name":"Adversarial Defense"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.10073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10073"}},"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/nisplab/at-bsl","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/NISPLab/AT-BSL","reach":{"status":"ok"}}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":6,"samples":[{"code_sha256_prefix":"54780edfe377217b","entry":"BSL","repo":"NISPLab/AT-BSL","repo_kind":"official","path":"at_bsl_loss.py","file_url":"https://github.com/NISPLab/AT-BSL/blob/HEAD/at_bsl_loss.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":"54780edfe377217b"}},{"code_sha256_prefix":"0f23e7e681845fe0","entry":"ResNet18","repo":"NISPLab/AT-BSL","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/NISPLab/AT-BSL/blob/HEAD/models/resnet.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":"0f23e7e681845fe0"}},{"code_sha256_prefix":"151b4b69a6a02555","entry":"eval_adv_test_whitebox","repo":"NISPLab/AT-BSL","repo_kind":"official","path":"pgd_attack.py","file_url":"https://github.com/NISPLab/AT-BSL/blob/HEAD/pgd_attack.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":"151b4b69a6a02555"}},{"code_sha256_prefix":"12252555e7643066","entry":"pgd_loss","repo":"NISPLab/AT-BSL","repo_kind":"official","path":"at_bsl_loss.py","file_url":"https://github.com/NISPLab/AT-BSL/blob/HEAD/at_bsl_loss.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":"12252555e7643066"}},{"code_sha256_prefix":"b83aa0df4382b430","entry":"ti_preact_resnet","repo":"NISPLab/AT-BSL","repo_kind":"official","path":"models/ti_preact_resnet.py","file_url":"https://github.com/NISPLab/AT-BSL/blob/HEAD/models/ti_preact_resnet.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":"b83aa0df4382b430"}},{"code_sha256_prefix":"f2dd3330391f0d13","entry":"load_tinyimagenet","repo":"NISPLab/AT-BSL","repo_kind":"official","path":"datasets/tiny_imagenet.py","file_url":"https://github.com/NISPLab/AT-BSL/blob/HEAD/datasets/tiny_imagenet.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":"f2dd3330391f0d13"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}