{"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/subspace-attack-exploiting-promising","title":"Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks","arxiv_id":"1906.04392","date":"2019-06-11","proceeding":"NeurIPS 2019 12","authors":["Ziang Yan","Yiwen Guo","Chang-Shui Zhang"],"abstract":"Unlike the white-box counterparts that are widely studied and readily accessible, adversarial examples in black-box settings are generally more Herculean on account of the difficulty of estimating gradients. Many methods achieve the task by issuing numerous queries to target classification systems, which makes the whole procedure costly and suspicious to the systems. In this paper, we aim at reducing the query complexity of black-box attacks in this category. We propose to exploit gradients of a few reference models which arguably span some promising search subspaces. Experimental results show that, in comparison with the state-of-the-arts, our method can gain up to 2x and 4x reductions in the requisite mean and medium numbers of queries with much lower failure rates even if the reference models are trained on a small and inadequate dataset disjoint to the one for training the victim model. Code and models for reproducing our results will be made publicly available.","url_abs":"https://arxiv.org/abs/1906.04392v1","url_pdf":"https://arxiv.org/pdf/1906.04392v1.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":"subspace-attack-exploiting-promising","repo_url":"https://github.com/ZiangYan/subspace-attack.pytorch","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"subspace-attack-exploiting-promising","repo_url":"https://github.com/epfl-ml-reproducers/subspace-attack-reproduction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.04392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.04392"}},"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/epfl-ml-reproducers/subspace-attack-reproduction","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZiangYan/subspace-attack.pytorch","reach":null}],"summary":{"ran_honours":1,"ran_fixture":1,"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":"b12b2cbd837d1105","entry":"gd_prior_step","repo":"ZiangYan/subspace-attack.pytorch","repo_kind":"official","path":"attack.py","file_url":"https://github.com/ZiangYan/subspace-attack.pytorch/blob/HEAD/attack.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b12b2cbd837d1105"}},{"code_sha256_prefix":"c0bd0f11c7d847e7","entry":"norm","repo":"ZiangYan/subspace-attack.pytorch","repo_kind":"official","path":"attack.py","file_url":"https://github.com/ZiangYan/subspace-attack.pytorch/blob/HEAD/attack.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":"c0bd0f11c7d847e7"}},{"code_sha256_prefix":"e9c0dd6c66f5cbbc","entry":"eg_prior_step","repo":"ZiangYan/subspace-attack.pytorch","repo_kind":"official","path":"attack.py","file_url":"https://github.com/ZiangYan/subspace-attack.pytorch/blob/HEAD/attack.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":"e9c0dd6c66f5cbbc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}