{"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/geoda-a-geometric-framework-for-black-box","title":"GeoDA: a geometric framework for black-box adversarial attacks","arxiv_id":"2003.06468","date":"2020-03-13","proceeding":"CVPR 2020 6","authors":["Ali Rahmati","Seyed-Mohsen Moosavi-Dezfooli","Pascal Frossard","Huaiyu Dai"],"abstract":"Adversarial examples are known as carefully perturbed images fooling image classifiers. We propose a geometric framework to generate adversarial examples in one of the most challenging black-box settings where the adversary can only generate a small number of queries, each of them returning the top-$1$ label of the classifier. Our framework is based on the observation that the decision boundary of deep networks usually has a small mean curvature in the vicinity of data samples. We propose an effective iterative algorithm to generate query-efficient black-box perturbations with small $\\ell_p$ norms for $p \\ge 1$, which is confirmed via experimental evaluations on state-of-the-art natural image classifiers. Moreover, for $p=2$, we theoretically show that our algorithm actually converges to the minimal $\\ell_2$-perturbation when the curvature of the decision boundary is bounded. We also obtain the optimal distribution of the queries over the iterations of the algorithm. Finally, experimental results confirm that our principled black-box attack algorithm performs better than state-of-the-art algorithms as it generates smaller perturbations with a reduced number of queries.","url_abs":"https://arxiv.org/abs/2003.06468v1","url_pdf":"https://arxiv.org/pdf/2003.06468v1.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":"geoda-a-geometric-framework-for-black-box","repo_url":"https://github.com/thisisalirah/GeoDA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.06468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.06468"}},"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/thisisalirah/GeoDA","reach":null}],"summary":{"ran_fixture":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"2a44b650a663361d","entry":"from_np_to_01","repo":"thisisalirah/GeoDA","repo_kind":"official","path":"GeoDA.py","file_url":"https://github.com/thisisalirah/GeoDA/blob/HEAD/GeoDA.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":"2a44b650a663361d"}},{"code_sha256_prefix":"839cb1e65b0caf9a","entry":"inv_tf","repo":"thisisalirah/GeoDA","repo_kind":"official","path":"GeoDA.py","file_url":"https://github.com/thisisalirah/GeoDA/blob/HEAD/GeoDA.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"839cb1e65b0caf9a"}},{"code_sha256_prefix":"cd943ae5de2d9972","entry":"topk_3D","repo":"thisisalirah/GeoDA","repo_kind":"official","path":"GeoDA.py","file_url":"https://github.com/thisisalirah/GeoDA/blob/HEAD/GeoDA.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":"cd943ae5de2d9972"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}