{"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/revisiting-adversarial-training-for-imagenet-1","title":"Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models","arxiv_id":"2303.01870","date":"2023-03-03","proceeding":"NeurIPS 2023 11","authors":["Naman D Singh","Francesco Croce","Matthias Hein"],"abstract":"While adversarial training has been extensively studied for ResNet architectures and low resolution datasets like CIFAR, much less is known for ImageNet. Given the recent debate about whether transformers are more robust than convnets, we revisit adversarial training on ImageNet comparing ViTs and ConvNeXts. Extensive experiments show that minor changes in architecture, most notably replacing PatchStem with ConvStem, and training scheme have a significant impact on the achieved robustness. These changes not only increase robustness in the seen $\\ell_\\infty$-threat model, but even more so improve generalization to unseen $\\ell_1/\\ell_2$-attacks. Our modified ConvNeXt, ConvNeXt + ConvStem, yields the most robust $\\ell_\\infty$-models across different ranges of model parameters and FLOPs, while our ViT + ConvStem yields the best generalization to unseen threat models.","url_abs":"https://arxiv.org/abs/2303.01870v2","url_pdf":"https://arxiv.org/pdf/2303.01870v2.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":"revisiting-adversarial-training-for-imagenet-1","repo_url":"https://github.com/nmndeep/revisiting-at","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convnext","method_name":"ConvNeXt"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.01870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.01870"}},"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/nmndeep/revisiting-at","reach":null}],"summary":{"ran_fixture":2,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"9590290f8fb5a3d5","entry":"interpolate_pos_encoding","repo":"nmndeep/revisiting-at","repo_kind":"official","path":"utils_architecture.py","file_url":"https://github.com/nmndeep/revisiting-at/blob/HEAD/utils_architecture.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9590290f8fb5a3d5"}},{"code_sha256_prefix":"129978316a52dfa9","entry":"normalize_model","repo":"nmndeep/revisiting-at","repo_kind":"official","path":"utils_architecture.py","file_url":"https://github.com/nmndeep/revisiting-at/blob/HEAD/utils_architecture.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"129978316a52dfa9"}},{"code_sha256_prefix":"54db0b9005599f07","entry":"timm_gelu","repo":"nmndeep/revisiting-at","repo_kind":"official","path":"utils_architecture.py","file_url":"https://github.com/nmndeep/revisiting-at/blob/HEAD/utils_architecture.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"54db0b9005599f07"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}