{"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/efficient-and-effective-augmentation-strategy","title":"Efficient and Effective Augmentation Strategy for Adversarial Training","arxiv_id":"2210.15318","date":"2022-10-27","proceeding":null,"authors":["Sravanti Addepalli","Samyak Jain","R. Venkatesh Babu"],"abstract":"Adversarial training of Deep Neural Networks is known to be significantly more data-hungry when compared to standard training. Furthermore, complex data augmentations such as AutoAugment, which have led to substantial gains in standard training of image classifiers, have not been successful with Adversarial Training. We first explain this contrasting behavior by viewing augmentation during training as a problem of domain generalization, and further propose Diverse Augmentation-based Joint Adversarial Training (DAJAT) to use data augmentations effectively in adversarial training. We aim to handle the conflicting goals of enhancing the diversity of the training dataset and training with data that is close to the test distribution by using a combination of simple and complex augmentations with separate batch normalization layers during training. We further utilize the popular Jensen-Shannon divergence loss to encourage the joint learning of the diverse augmentations, thereby allowing simple augmentations to guide the learning of complex ones. Lastly, to improve the computational efficiency of the proposed method, we propose and utilize a two-step defense, Ascending Constraint Adversarial Training (ACAT), that uses an increasing epsilon schedule and weight-space smoothing to prevent gradient masking. The proposed method DAJAT achieves substantially better robustness-accuracy trade-off when compared to existing methods on the RobustBench Leaderboard on ResNet-18 and WideResNet-34-10. The code for implementing DAJAT is available here: https://github.com/val-iisc/DAJAT.","url_abs":"https://arxiv.org/abs/2210.15318v1","url_pdf":"https://arxiv.org/pdf/2210.15318v1.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":"efficient-and-effective-augmentation-strategy","repo_url":"https://github.com/val-iisc/dajat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"efficient-and-effective-augmentation-strategy","repo_url":"https://github.com/Trustworthy-ML-Lab/Interpretability-Guided-Defense","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"}],"methods":[{"method_slug":"autoaugment","method_name":"AutoAugment"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.15318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15318"}},"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":"deterministic:regex_extraction","url":"https://github.com/val-iisc/DAJAT","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Trustworthy-ML-Lab/Interpretability-Guided-Defense","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/val-iisc/dajat","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":5},"by_repo_kind":{"official":{"samples":7,"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":"4170809219439d13","entry":"diff_in_weights","repo":"val-iisc/DAJAT","repo_kind":"official","path":"utils_awp.py","file_url":"https://github.com/val-iisc/DAJAT/blob/HEAD/utils_awp.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4170809219439d13"}},{"code_sha256_prefix":"3cbdd3b190b16350","entry":"get_mean_and_std","repo":"val-iisc/DAJAT","repo_kind":"official","path":"utils/misc.py","file_url":"https://github.com/val-iisc/DAJAT/blob/HEAD/utils/misc.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3cbdd3b190b16350"}},{"code_sha256_prefix":"986f87e3f22773c4","entry":"ResNet18","repo":"val-iisc/DAJAT","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/val-iisc/DAJAT/blob/HEAD/models/resnet.py","link_basis":"harvester_set","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":"986f87e3f22773c4"}},{"code_sha256_prefix":"944f20d0ca70a84f","entry":"WideResNet34","repo":"val-iisc/DAJAT","repo_kind":"official","path":"models/wideresnet.py","file_url":"https://github.com/val-iisc/DAJAT/blob/HEAD/models/wideresnet.py","link_basis":"harvester_set","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":"944f20d0ca70a84f"}},{"code_sha256_prefix":"21cb458e511468b6","entry":"get_mean_and_std_modified","repo":"val-iisc/DAJAT","repo_kind":"official","path":"utils/misc.py","file_url":"https://github.com/val-iisc/DAJAT/blob/HEAD/utils/misc.py","link_basis":"harvester_set","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":"21cb458e511468b6"}},{"code_sha256_prefix":"093c9b30736e13f4","entry":"plot_overlap","repo":"val-iisc/DAJAT","repo_kind":"official","path":"utils/logger.py","file_url":"https://github.com/val-iisc/DAJAT/blob/HEAD/utils/logger.py","link_basis":"harvester_set","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":"093c9b30736e13f4"}},{"code_sha256_prefix":"28322e1b03619b6d","entry":"use_default","repo":"val-iisc/DAJAT","repo_kind":"official","path":"defaults.py","file_url":"https://github.com/val-iisc/DAJAT/blob/HEAD/defaults.py","link_basis":"harvester_set","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":"28322e1b03619b6d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}