{"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/practical-evaluation-of-adversarial","title":"Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack","arxiv_id":"2203.05154","date":"2022-03-10","proceeding":"CVPR 2022 1","authors":["Ye Liu","Yaya Cheng","Lianli Gao","Xianglong Liu","Qilong Zhang","Jingkuan Song"],"abstract":"Defense models against adversarial attacks have grown significantly, but the lack of practical evaluation methods has hindered progress. Evaluation can be defined as looking for defense models' lower bound of robustness given a budget number of iterations and a test dataset. A practical evaluation method should be convenient (i.e., parameter-free), efficient (i.e., fewer iterations) and reliable (i.e., approaching the lower bound of robustness). Towards this target, we propose a parameter-free Adaptive Auto Attack (A$^3$) evaluation method which addresses the efficiency and reliability in a test-time-training fashion. Specifically, by observing that adversarial examples to a specific defense model follow some regularities in their starting points, we design an Adaptive Direction Initialization strategy to speed up the evaluation. Furthermore, to approach the lower bound of robustness under the budget number of iterations, we propose an online statistics-based discarding strategy that automatically identifies and abandons hard-to-attack images. Extensive experiments demonstrate the effectiveness of our A$^3$. Particularly, we apply A$^3$ to nearly 50 widely-used defense models. By consuming much fewer iterations than existing methods, i.e., $1/10$ on average (10$\\times$ speed up), we achieve lower robust accuracy in all cases. Notably, we won $\\textbf{first place}$ out of 1681 teams in CVPR 2021 White-box Adversarial Attacks on Defense Models competitions with this method. Code is available at: $\\href{https://github.com/liuye6666/adaptive_auto_attack}{https://github.com/liuye6666/adaptive\\_auto\\_attack}$","url_abs":"https://arxiv.org/abs/2203.05154v3","url_pdf":"https://arxiv.org/pdf/2203.05154v3.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":"practical-evaluation-of-adversarial","repo_url":"https://github.com/liuye6666/adaptive_auto_attack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2203.05154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05154"}},"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/fra31/auto-attack","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liuye6666/adaptive_auto_attack","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/liuye6666/adaptive","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"ran":2,"ran_fixture":2,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":3,"repositories":1},"found_in_text":{"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":0,"samples":[{"code_sha256_prefix":"1f1c0fb5fee05251","entry":"EvaluationState","repo":"fra31/auto-attack","repo_kind":"found_in_text","path":"autoattack/autoattack.py","file_url":"https://github.com/fra31/auto-attack/blob/HEAD/autoattack/autoattack.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1f1c0fb5fee05251"}},{"code_sha256_prefix":"1d523ea323a6b340","entry":"lp_norm","repo":"liuye6666/adaptive_auto_attack","repo_kind":"official","path":"Adaptive_Auto_Attack_main.py","file_url":"https://github.com/liuye6666/adaptive_auto_attack/blob/HEAD/Adaptive_Auto_Attack_main.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1d523ea323a6b340"}},{"code_sha256_prefix":"c832edfa8ce9c69d","entry":"margin_loss","repo":"liuye6666/adaptive_auto_attack","repo_kind":"official","path":"Adaptive_Auto_Attack_main.py","file_url":"https://github.com/liuye6666/adaptive_auto_attack/blob/HEAD/Adaptive_Auto_Attack_main.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c832edfa8ce9c69d"}},{"code_sha256_prefix":"852403b999b50d53","entry":"normalize_x","repo":"liuye6666/adaptive_auto_attack","repo_kind":"official","path":"Adaptive_Auto_Attack_main.py","file_url":"https://github.com/liuye6666/adaptive_auto_attack/blob/HEAD/Adaptive_Auto_Attack_main.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"852403b999b50d53"}},{"code_sha256_prefix":"5b1ee32a9bce8b64","entry":"AAA_white_box","repo":"liuye6666/adaptive_auto_attack","repo_kind":"official","path":"Adaptive_Auto_Attack_main.py","file_url":"https://github.com/liuye6666/adaptive_auto_attack/blob/HEAD/Adaptive_Auto_Attack_main.py","link_basis":"first_harvest_node","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":"5b1ee32a9bce8b64"}},{"code_sha256_prefix":"d98c529d0851b047","entry":"AutoAttack","repo":"fra31/auto-attack","repo_kind":"found_in_text","path":"autoattack/autoattack.py","file_url":"https://github.com/fra31/auto-attack/blob/HEAD/autoattack/autoattack.py","link_basis":"first_harvest_node","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":"d98c529d0851b047"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}