{"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/adversarial-distributional-training-for","title":"Adversarial Distributional Training for Robust Deep Learning","arxiv_id":"2002.05999","date":"2020-02-14","proceeding":"NeurIPS 2020 12","authors":["Yinpeng Dong","Zhijie Deng","Tianyu Pang","Hang Su","Jun Zhu"],"abstract":"Adversarial training (AT) is among the most effective techniques to improve model robustness by augmenting training data with adversarial examples. However, most existing AT methods adopt a specific attack to craft adversarial examples, leading to the unreliable robustness against other unseen attacks. Besides, a single attack algorithm could be insufficient to explore the space of perturbations. In this paper, we introduce adversarial distributional training (ADT), a novel framework for learning robust models. ADT is formulated as a minimax optimization problem, where the inner maximization aims to learn an adversarial distribution to characterize the potential adversarial examples around a natural one under an entropic regularizer, and the outer minimization aims to train robust models by minimizing the expected loss over the worst-case adversarial distributions. Through a theoretical analysis, we develop a general algorithm for solving ADT, and present three approaches for parameterizing the adversarial distributions, ranging from the typical Gaussian distributions to the flexible implicit ones. Empirical results on several benchmarks validate the effectiveness of ADT compared with the state-of-the-art AT methods.","url_abs":"https://arxiv.org/abs/2002.05999v2","url_pdf":"https://arxiv.org/pdf/2002.05999v2.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":"adversarial-distributional-training-for","repo_url":"https://github.com/dongyp13/Adversarial-Distributional-Training","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.05999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.05999"}},"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/dongyp13/Adversarial-Distributional-Training","reach":null}],"summary":{"ran_draft_wrong":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":"425cd347c04fa255","entry":"adt_loss","repo":"dongyp13/adversarial-distributional-training","repo_kind":"official","path":"adt_exp.py","file_url":"https://github.com/dongyp13/adversarial-distributional-training/blob/HEAD/adt_exp.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"425cd347c04fa255"}},{"code_sha256_prefix":"3ab4f8401e4868aa","entry":"generate_pert","repo":"dongyp13/Adversarial-Distributional-Training","repo_kind":"official","path":"adt_expam.py","file_url":"https://github.com/dongyp13/Adversarial-Distributional-Training/blob/HEAD/adt_expam.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ab4f8401e4868aa"}},{"code_sha256_prefix":"e19cfeec2f5495fa","entry":"one_hot_tensor","repo":"dongyp13/adversarial-distributional-training","repo_kind":"official","path":"evaluate_attacks.py","file_url":"https://github.com/dongyp13/adversarial-distributional-training/blob/HEAD/evaluate_attacks.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":"e19cfeec2f5495fa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}