{"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/structured-adversarial-attack-towards-general","title":"Structured Adversarial Attack: Towards General Implementation and Better Interpretability","arxiv_id":"1808.01664","date":"2018-08-05","proceeding":"ICLR 2019 5","authors":["Kaidi Xu","Sijia Liu","Pu Zhao","Pin-Yu Chen","huan zhang","Quanfu Fan","Deniz Erdogmus","Yanzhi Wang","Xue Lin"],"abstract":"When generating adversarial examples to attack deep neural networks (DNNs),\nLp norm of the added perturbation is usually used to measure the similarity\nbetween original image and adversarial example. However, such adversarial\nattacks perturbing the raw input spaces may fail to capture structural\ninformation hidden in the input. This work develops a more general attack\nmodel, i.e., the structured attack (StrAttack), which explores group sparsity\nin adversarial perturbations by sliding a mask through images aiming for\nextracting key spatial structures. An ADMM (alternating direction method of\nmultipliers)-based framework is proposed that can split the original problem\ninto a sequence of analytically solvable subproblems and can be generalized to\nimplement other attacking methods. Strong group sparsity is achieved in\nadversarial perturbations even with the same level of Lp norm distortion as the\nstate-of-the-art attacks. We demonstrate the effectiveness of StrAttack by\nextensive experimental results onMNIST, CIFAR-10, and ImageNet. We also show\nthat StrAttack provides better interpretability (i.e., better correspondence\nwith discriminative image regions)through adversarial saliency map (Papernot et\nal., 2016b) and class activation map(Zhou et al., 2016).","url_abs":"http://arxiv.org/abs/1808.01664v3","url_pdf":"http://arxiv.org/pdf/1808.01664v3.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":"structured-adversarial-attack-towards-general","repo_url":"https://github.com/KaidiXu/StrAttack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"}],"methods":[{"method_slug":"admm","method_name":"ADMM"},{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.01664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.01664"}},"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/KaidiXu/StrAttack","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":1,"samples":[{"code_sha256_prefix":"8da19e9d83604707","entry":"generate_data","repo":"KaidiXu/StrAttack","repo_kind":"official","path":"test_attack_iclr.py","file_url":"https://github.com/KaidiXu/StrAttack/blob/HEAD/test_attack_iclr.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":"8da19e9d83604707"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}