{"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/uniformly-stable-algorithms-for-adversarial","title":"Uniformly Stable Algorithms for Adversarial Training and Beyond","arxiv_id":"2405.01817","date":"2024-05-03","proceeding":null,"authors":["Jiancong Xiao","Jiawei Zhang","Zhi-Quan Luo","Asuman Ozdaglar"],"abstract":"In adversarial machine learning, neural networks suffer from a significant issue known as robust overfitting, where the robust test accuracy decreases over epochs (Rice et al., 2020). Recent research conducted by Xing et al.,2021; Xiao et al., 2022 has focused on studying the uniform stability of adversarial training. Their investigations revealed that SGD-based adversarial training fails to exhibit uniform stability, and the derived stability bounds align with the observed phenomenon of robust overfitting in experiments. This motivates us to develop uniformly stable algorithms specifically tailored for adversarial training. To this aim, we introduce Moreau envelope-$\\mathcal{A}$, a variant of the Moreau Envelope-type algorithm. We employ a Moreau envelope function to reframe the original problem as a min-min problem, separating the non-strong convexity and non-smoothness of the adversarial loss. Then, this approach alternates between solving the inner and outer minimization problems to achieve uniform stability without incurring additional computational overhead. In practical scenarios, we show the efficacy of ME-$\\mathcal{A}$ in mitigating the issue of robust overfitting. Beyond its application in adversarial training, this represents a fundamental result in uniform stability analysis, as ME-$\\mathcal{A}$ is the first algorithm to exhibit uniform stability for weakly-convex, non-smooth problems.","url_abs":"https://arxiv.org/abs/2405.01817v1","url_pdf":"https://arxiv.org/pdf/2405.01817v1.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":"uniformly-stable-algorithms-for-adversarial","repo_url":"https://github.com/jiancongxiao/moreau-envelope-sgd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2405.01817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.01817"}},"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/jiancongxiao/moreau-envelope-sgd","reach":{"status":"ok"}}],"summary":{"ran":2,"ran_draft_wrong":1,"ran_violates":1,"ran_fixture":1,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":9,"ran":6,"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":9,"samples":[{"code_sha256_prefix":"1153837ba4a94242","entry":"PreActResNet18","repo":"jiancongxiao/moreau-envelope-sgd","repo_kind":"official","path":"adversarial_robustness_overfitting/preactresnet.py","file_url":"https://github.com/jiancongxiao/moreau-envelope-sgd/blob/HEAD/adversarial_robustness_overfitting/preactresnet.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":"1153837ba4a94242"}},{"code_sha256_prefix":"9aa516330b945a07","entry":"accuracy","repo":"jiancongxiao/moreau-envelope-sgd","repo_kind":"official","path":"adversarial_robustness_uncovering/core/metrics.py","file_url":"https://github.com/jiancongxiao/moreau-envelope-sgd/blob/HEAD/adversarial_robustness_uncovering/core/metrics.py","link_basis":"plan_row","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":"9aa516330b945a07"}},{"code_sha256_prefix":"6e59364a7cf6008f","entry":"check_bn","repo":"jiancongxiao/moreau-envelope-sgd","repo_kind":"official","path":"adversarial_robustness_overfitting/swa_utils.py","file_url":"https://github.com/jiancongxiao/moreau-envelope-sgd/blob/HEAD/adversarial_robustness_overfitting/swa_utils.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6e59364a7cf6008f"}},{"code_sha256_prefix":"b20f1357b1d8dbf8","entry":"mixup_data","repo":"jiancongxiao/moreau-envelope-sgd","repo_kind":"official","path":"adversarial_robustness_overfitting/mea_train_cifar.py","file_url":"https://github.com/jiancongxiao/moreau-envelope-sgd/blob/HEAD/adversarial_robustness_overfitting/mea_train_cifar.py","link_basis":"plan_row","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":"b20f1357b1d8dbf8"}},{"code_sha256_prefix":"1e0eb41fc8899d05","entry":"pad","repo":"jiancongxiao/moreau-envelope-sgd","repo_kind":"official","path":"adversarial_robustness_overfitting/utils.py","file_url":"https://github.com/jiancongxiao/moreau-envelope-sgd/blob/HEAD/adversarial_robustness_overfitting/utils.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":"1e0eb41fc8899d05"}},{"code_sha256_prefix":"6c582cf17bee2767","entry":"prox_term","repo":"jiancongxiao/moreau-envelope-sgd","repo_kind":"official","path":"adversarial_robustness_overfitting/swa_utils.py","file_url":"https://github.com/jiancongxiao/moreau-envelope-sgd/blob/HEAD/adversarial_robustness_overfitting/swa_utils.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6c582cf17bee2767"}},{"code_sha256_prefix":"8a93e041134b597a","entry":"clamp","repo":"jiancongxiao/moreau-envelope-sgd","repo_kind":"official","path":"adversarial_robustness_overfitting/mea_train_cifar.py","file_url":"https://github.com/jiancongxiao/moreau-envelope-sgd/blob/HEAD/adversarial_robustness_overfitting/mea_train_cifar.py","link_basis":"plan_row","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":"8a93e041134b597a"}},{"code_sha256_prefix":"d2a4ac781b2a9628","entry":"normalise","repo":"jiancongxiao/moreau-envelope-sgd","repo_kind":"official","path":"adversarial_robustness_overfitting/utils.py","file_url":"https://github.com/jiancongxiao/moreau-envelope-sgd/blob/HEAD/adversarial_robustness_overfitting/utils.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":"d2a4ac781b2a9628"}},{"code_sha256_prefix":"c0f89c373fea538a","entry":"transpose","repo":"jiancongxiao/moreau-envelope-sgd","repo_kind":"official","path":"adversarial_robustness_overfitting/utils.py","file_url":"https://github.com/jiancongxiao/moreau-envelope-sgd/blob/HEAD/adversarial_robustness_overfitting/utils.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":"c0f89c373fea538a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}