{"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/attacking-deep-networks-with-surrogate-based-1","title":"Attacking deep networks with surrogate-based adversarial black-box methods is easy","arxiv_id":"2203.08725","date":"2022-03-16","proceeding":"ICLR 2022 4","authors":["Nicholas A. Lord","Romain Mueller","Luca Bertinetto"],"abstract":"A recent line of work on black-box adversarial attacks has revived the use of transfer from surrogate models by integrating it into query-based search. However, we find that existing approaches of this type underperform their potential, and can be overly complicated besides. Here, we provide a short and simple algorithm which achieves state-of-the-art results through a search which uses the surrogate network's class-score gradients, with no need for other priors or heuristics. The guiding assumption of the algorithm is that the studied networks are in a fundamental sense learning similar functions, and that a transfer attack from one to the other should thus be fairly \"easy\". This assumption is validated by the extremely low query counts and failure rates achieved: e.g. an untargeted attack on a VGG-16 ImageNet network using a ResNet-152 as the surrogate yields a median query count of 6 at a success rate of 99.9%. Code is available at https://github.com/fiveai/GFCS.","url_abs":"https://arxiv.org/abs/2203.08725v1","url_pdf":"https://arxiv.org/pdf/2203.08725v1.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":"attacking-deep-networks-with-surrogate-based-1","repo_url":"https://github.com/fiveai/gfcs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.08725","atlas_url":"https://app.syntology.ai/?focus=2203.08725","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.08725"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/fiveai/GFCS","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fiveai/gfcs","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":"2f6dca5e8c05e7eb","entry":"Interpolate","repo":"fiveai/gfcs","repo_kind":"official","path":"rgf_variants_pytorch.py","file_url":"https://github.com/fiveai/gfcs/blob/HEAD/rgf_variants_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2f6dca5e8c05e7eb"}},{"code_sha256_prefix":"700b4a8ed64b8703","entry":"Normalise","repo":"fiveai/gfcs","repo_kind":"official","path":"rgf_variants_pytorch.py","file_url":"https://github.com/fiveai/gfcs/blob/HEAD/rgf_variants_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"700b4a8ed64b8703"}},{"code_sha256_prefix":"0fb1b2ef18888998","entry":"generate_data_transform","repo":"fiveai/gfcs","repo_kind":"official","path":"rgf_variants_pytorch.py","file_url":"https://github.com/fiveai/gfcs/blob/HEAD/rgf_variants_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"0fb1b2ef18888998"}},{"code_sha256_prefix":"7e850e4ff2785586","entry":"p_rgf_pytorch","repo":"fiveai/gfcs","repo_kind":"official","path":"rgf_variants_pytorch.py","file_url":"https://github.com/fiveai/gfcs/blob/HEAD/rgf_variants_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7e850e4ff2785586"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}