{"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/prior-guided-adversarial-initialization-for","title":"Prior-Guided Adversarial Initialization for Fast Adversarial Training","arxiv_id":"2207.08859","date":"2022-07-18","proceeding":null,"authors":["Xiaojun Jia","Yong Zhang","Xingxing Wei","Baoyuan Wu","Ke Ma","Jue Wang","Xiaochun Cao"],"abstract":"Fast adversarial training (FAT) effectively improves the efficiency of standard adversarial training (SAT). However, initial FAT encounters catastrophic overfitting, i.e.,the robust accuracy against adversarial attacks suddenly and dramatically decreases. Though several FAT variants spare no effort to prevent overfitting, they sacrifice much calculation cost. In this paper, we explore the difference between the training processes of SAT and FAT and observe that the attack success rate of adversarial examples (AEs) of FAT gets worse gradually in the late training stage, resulting in overfitting. The AEs are generated by the fast gradient sign method (FGSM) with a zero or random initialization. Based on the observation, we propose a prior-guided FGSM initialization method to avoid overfitting after investigating several initialization strategies, improving the quality of the AEs during the whole training process. The initialization is formed by leveraging historically generated AEs without additional calculation cost. We further provide a theoretical analysis for the proposed initialization method. We also propose a simple yet effective regularizer based on the prior-guided initialization,i.e., the currently generated perturbation should not deviate too much from the prior-guided initialization. The regularizer adopts both historical and current adversarial perturbations to guide the model learning. Evaluations on four datasets demonstrate that the proposed method can prevent catastrophic overfitting and outperform state-of-the-art FAT methods. The code is released at https://github.com/jiaxiaojunQAQ/FGSM-PGI.","url_abs":"https://arxiv.org/abs/2207.08859v1","url_pdf":"https://arxiv.org/pdf/2207.08859v1.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":"prior-guided-adversarial-initialization-for","repo_url":"https://github.com/jiaxiaojunqaq/fgsm-pgi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"adversarial-attack-on-video-classification","task_name":"Adversarial Attack on Video Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.08859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.08859"}},"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/jiaxiaojunqaq/fgsm-pgi","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/jiaxiaojunQAQ/FGSM-PGI","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"b1e5593d09257e4e","entry":"LabelSmoothLoss","repo":"jiaxiaojunQAQ/FGSM-PGI","repo_kind":"official","path":"FGSM_MEP.py","file_url":"https://github.com/jiaxiaojunQAQ/FGSM-PGI/blob/HEAD/FGSM_MEP.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b1e5593d09257e4e"}},{"code_sha256_prefix":"05737f0d296b99b5","entry":"_label_smoothing","repo":"jiaxiaojunQAQ/FGSM-PGI","repo_kind":"official","path":"FGSM_MEP.py","file_url":"https://github.com/jiaxiaojunQAQ/FGSM-PGI/blob/HEAD/FGSM_MEP.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"05737f0d296b99b5"}},{"code_sha256_prefix":"4ee20683cac813a9","entry":"get_args","repo":"jiaxiaojunQAQ/FGSM-PGI","repo_kind":"official","path":"FGSM_MEP.py","file_url":"https://github.com/jiaxiaojunQAQ/FGSM-PGI/blob/HEAD/FGSM_MEP.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":"4ee20683cac813a9"}},{"code_sha256_prefix":"1ee03925b8eef465","entry":"main","repo":"jiaxiaojunQAQ/FGSM-PGI","repo_kind":"official","path":"FGSM_MEP.py","file_url":"https://github.com/jiaxiaojunQAQ/FGSM-PGI/blob/HEAD/FGSM_MEP.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":"1ee03925b8eef465"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}