{"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/improving-generalization-of-adversarial","title":"Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning","arxiv_id":"2308.02533","date":"2023-08-01","proceeding":"ICCV 2023 1","authors":["Kaijie Zhu","Jindong Wang","Xixu Hu","Xing Xie","Ge Yang"],"abstract":"Deep neural networks are susceptible to adversarial examples, posing a significant security risk in critical applications. Adversarial Training (AT) is a well-established technique to enhance adversarial robustness, but it often comes at the cost of decreased generalization ability. This paper proposes Robustness Critical Fine-Tuning (RiFT), a novel approach to enhance generalization without compromising adversarial robustness. The core idea of RiFT is to exploit the redundant capacity for robustness by fine-tuning the adversarially trained model on its non-robust-critical module. To do so, we introduce module robust criticality (MRC), a measure that evaluates the significance of a given module to model robustness under worst-case weight perturbations. Using this measure, we identify the module with the lowest MRC value as the non-robust-critical module and fine-tune its weights to obtain fine-tuned weights. Subsequently, we linearly interpolate between the adversarially trained weights and fine-tuned weights to derive the optimal fine-tuned model weights. We demonstrate the efficacy of RiFT on ResNet18, ResNet34, and WideResNet34-10 models trained on CIFAR10, CIFAR100, and Tiny-ImageNet datasets. Our experiments show that \\method can significantly improve both generalization and out-of-distribution robustness by around 1.5% while maintaining or even slightly enhancing adversarial robustness. Code is available at https://github.com/microsoft/robustlearn.","url_abs":"https://arxiv.org/abs/2308.02533v1","url_pdf":"https://arxiv.org/pdf/2308.02533v1.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":"improving-generalization-of-adversarial","repo_url":"https://github.com/microsoft/robustlearn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2308.02533","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.02533"}},"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/microsoft/robustlearn","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Immortalise/RiFT","reach":{"status":"ok"}}],"summary":{"ran":4,"unverified":2},"by_repo_kind":{"found_in_text":{"samples":6,"ran":4,"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":6,"samples":[{"code_sha256_prefix":"5b545f16f72c1645","entry":"DenseNet121","repo":"Immortalise/RiFT","repo_kind":"found_in_text","path":"models/densenet.py","file_url":"https://github.com/Immortalise/RiFT/blob/HEAD/models/densenet.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":"5b545f16f72c1645"}},{"code_sha256_prefix":"05fe49b9f6cb6b38","entry":"DenseNet50","repo":"Immortalise/RiFT","repo_kind":"found_in_text","path":"models/densenet.py","file_url":"https://github.com/Immortalise/RiFT/blob/HEAD/models/densenet.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":"05fe49b9f6cb6b38"}},{"code_sha256_prefix":"4304a326c593f8db","entry":"drop_connect","repo":"Immortalise/RiFT","repo_kind":"found_in_text","path":"models/efficientnet.py","file_url":"https://github.com/Immortalise/RiFT/blob/HEAD/models/efficientnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4304a326c593f8db"}},{"code_sha256_prefix":"8737c82de631cffc","entry":"swish","repo":"Immortalise/RiFT","repo_kind":"found_in_text","path":"models/efficientnet.py","file_url":"https://github.com/Immortalise/RiFT/blob/HEAD/models/efficientnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8737c82de631cffc"}},{"code_sha256_prefix":"c7da9a5b14f0e084","entry":"create_dataloader","repo":"Immortalise/RiFT","repo_kind":"found_in_text","path":"dataloader.py","file_url":"https://github.com/Immortalise/RiFT/blob/HEAD/dataloader.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":"c7da9a5b14f0e084"}},{"code_sha256_prefix":"638459c6b58120a9","entry":"create_model","repo":"Immortalise/RiFT","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/Immortalise/RiFT/blob/HEAD/model.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":"638459c6b58120a9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}