{"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/overfitting-or-underfitting-understand","title":"Overfitting or Underfitting? Understand Robustness Drop in Adversarial Training","arxiv_id":"2010.08034","date":"2020-10-15","proceeding":null,"authors":["Zichao Li","Liyuan Liu","chengyu dong","Jingbo Shang"],"abstract":"Our goal is to understand why the robustness drops after conducting adversarial training for too long. Although this phenomenon is commonly explained as overfitting, our analysis suggest that its primary cause is perturbation underfitting. We observe that after training for too long, FGSM-generated perturbations deteriorate into random noise. Intuitively, since no parameter updates are made to strengthen the perturbation generator, once this process collapses, it could be trapped in such local optima. Also, sophisticating this process could mostly avoid the robustness drop, which supports that this phenomenon is caused by underfitting instead of overfitting. In the light of our analyses, we propose APART, an adaptive adversarial training framework, which parameterizes perturbation generation and progressively strengthens them. Shielding perturbations from underfitting unleashes the potential of our framework. In our experiments, APART provides comparable or even better robustness than PGD-10, with only about 1/4 of its computational cost.","url_abs":"https://arxiv.org/abs/2010.08034v1","url_pdf":"https://arxiv.org/pdf/2010.08034v1.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":"overfitting-or-underfitting-understand","repo_url":"https://github.com/zichaoli/APART","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"overfitting-or-underfitting-understand","repo_url":"https://github.com/optimization-for-data-driven-science/dair","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.08034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.08034"}},"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/optimization-for-data-driven-science/dair","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zichaoli/APART","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"ran":1,"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":"eda67bbf007849b8","entry":"atta_aug","repo":"zichaoli/APART","repo_kind":"official","path":"adaptive_data_aug.py","file_url":"https://github.com/zichaoli/APART/blob/HEAD/adaptive_data_aug.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eda67bbf007849b8"}},{"code_sha256_prefix":"cd121dba2366ef98","entry":"atta_aug_trans","repo":"zichaoli/APART","repo_kind":"official","path":"adaptive_data_aug.py","file_url":"https://github.com/zichaoli/APART/blob/HEAD/adaptive_data_aug.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cd121dba2366ef98"}},{"code_sha256_prefix":"5a018a3a06e619c0","entry":"inverse_atta_aug","repo":"zichaoli/APART","repo_kind":"official","path":"adaptive_data_aug.py","file_url":"https://github.com/zichaoli/APART/blob/HEAD/adaptive_data_aug.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5a018a3a06e619c0"}},{"code_sha256_prefix":"0fcb1e999f8f49a0","entry":"load_pading_training_data","repo":"zichaoli/APART","repo_kind":"official","path":"cifar_dataloader.py","file_url":"https://github.com/zichaoli/APART/blob/HEAD/cifar_dataloader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0fcb1e999f8f49a0"}},{"code_sha256_prefix":"bdaf671659de92ff","entry":"preact20","repo":"zichaoli/APART","repo_kind":"official","path":"models/preresnet.py","file_url":"https://github.com/zichaoli/APART/blob/HEAD/models/preresnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bdaf671659de92ff"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}