{"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/curriculum-adversarial-training","title":"Curriculum Adversarial Training","arxiv_id":"1805.04807","date":"2018-05-13","proceeding":null,"authors":["Qi-Zhi Cai","Min Du","Chang Liu","Dawn Song"],"abstract":"Recently, deep learning has been applied to many security-sensitive\napplications, such as facial authentication. The existence of adversarial\nexamples hinders such applications. The state-of-the-art result on defense\nshows that adversarial training can be applied to train a robust model on MNIST\nagainst adversarial examples; but it fails to achieve a high empirical\nworst-case accuracy on a more complex task, such as CIFAR-10 and SVHN. In our\nwork, we propose curriculum adversarial training (CAT) to resolve this issue.\nThe basic idea is to develop a curriculum of adversarial examples generated by\nattacks with a wide range of strengths. With two techniques to mitigate the\nforgetting and the generalization issues, we demonstrate that CAT can improve\nthe prior art's empirical worst-case accuracy by a large margin of 25% on\nCIFAR-10 and 35% on SVHN. At the same, the model's performance on\nnon-adversarial inputs is comparable to the state-of-the-art models.","url_abs":"http://arxiv.org/abs/1805.04807v1","url_pdf":"http://arxiv.org/pdf/1805.04807v1.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":"curriculum-adversarial-training","repo_url":"https://github.com/sunblaze-ucb/curriculum-adversarial-training-CAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"curriculum-adversarial-training","repo_url":"https://github.com/zjfheart/Friendly-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=1805.04807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.04807"}},"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/Friendly-Adversarial-Training","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sunblaze-ucb/curriculum-adversarial-training-CAT","reach":null}],"summary":{"ran_honours":1,"unverified":1},"by_repo_kind":{"listed":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"3aebb0f46a180c15","entry":"getSec","repo":"sunblaze-ucb/curriculum-adversarial-training-CAT","repo_kind":"listed","path":"test_all_worstcaseacc.py","file_url":"https://github.com/sunblaze-ucb/curriculum-adversarial-training-CAT/blob/HEAD/test_all_worstcaseacc.py","link_basis":"first_harvest_node","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":"3aebb0f46a180c15"}},{"code_sha256_prefix":"545f115890b6f5a6","entry":"resumeFrom","repo":"sunblaze-ucb/curriculum-adversarial-training-CAT","repo_kind":"listed","path":"advtrain_all.py","file_url":"https://github.com/sunblaze-ucb/curriculum-adversarial-training-CAT/blob/HEAD/advtrain_all.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":"545f115890b6f5a6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}