{"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/querynet-an-efficient-attack-framework-with","title":"Query Attack by Multi-Identity Surrogates","arxiv_id":"2105.15010","date":"2021-05-31","proceeding":null,"authors":["Sizhe Chen","Zhehao Huang","Qinghua Tao","Xiaolin Huang"],"abstract":"Deep Neural Networks (DNNs) are acknowledged as vulnerable to adversarial attacks, while the existing black-box attacks require extensive queries on the victim DNN to achieve high success rates. For query-efficiency, surrogate models of the victim are used to generate transferable Adversarial Examples (AEs) because of their Gradient Similarity (GS), i.e., surrogates' attack gradients are similar to the victim's ones. However, it is generally neglected to exploit their similarity on outputs, namely the Prediction Similarity (PS), to filter out inefficient queries by surrogates without querying the victim. To jointly utilize and also optimize surrogates' GS and PS, we develop QueryNet, a unified attack framework that can significantly reduce queries. QueryNet creatively attacks by multi-identity surrogates, i.e., crafts several AEs for one sample by different surrogates, and also uses surrogates to decide on the most promising AE for the query. After that, the victim's query feedback is accumulated to optimize not only surrogates' parameters but also their architectures, enhancing both the GS and the PS. Although QueryNet has no access to pre-trained surrogates' prior, it reduces queries by averagely about an order of magnitude compared to alternatives within an acceptable time, according to our comprehensive experiments: 11 victims (including two commercial models) on MNIST/CIFAR10/ImageNet, allowing only 8-bit image queries, and no access to the victim's training data. The code is available at https://github.com/Sizhe-Chen/QueryNet.","url_abs":"https://arxiv.org/abs/2105.15010v5","url_pdf":"https://arxiv.org/pdf/2105.15010v5.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":"querynet-an-efficient-attack-framework-with","repo_url":"https://github.com/allenchen1998/querynet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"querynet-an-efficient-attack-framework-with","repo_url":"https://github.com/sizhe-chen/querynet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"ae","method_name":"AE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.15010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.15010"}},"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/allenchen1998/querynet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sizhe-chen/querynet","reach":null}],"summary":{"ran":2,"ran_draft_wrong":1,"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":8,"ran":4,"repositories":2}},"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":"e7ef53e9c5847e3e","entry":"adjust_lr","repo":"allenchen1998/querynet","repo_kind":"official","path":"PCDARTS/train_imagenet.py","file_url":"https://github.com/allenchen1998/querynet/blob/HEAD/PCDARTS/train_imagenet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e7ef53e9c5847e3e"}},{"code_sha256_prefix":"b9da06d4f527dd6c","entry":"channel_shuffle","repo":"allenchen1998/querynet","repo_kind":"official","path":"PCDARTS/model_search.py","file_url":"https://github.com/allenchen1998/querynet/blob/HEAD/PCDARTS/model_search.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b9da06d4f527dd6c"}},{"code_sha256_prefix":"176dfa1e026fb136","entry":"dense_to_onehot","repo":"allenchen1998/querynet","repo_kind":"official","path":"utils.py","file_url":"https://github.com/allenchen1998/querynet/blob/HEAD/utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"176dfa1e026fb136"}},{"code_sha256_prefix":"4fe62c36ed4bbecd","entry":"p_selection","repo":"sizhe-chen/querynet","repo_kind":"official","path":"querynet.py","file_url":"https://github.com/sizhe-chen/querynet/blob/HEAD/querynet.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4fe62c36ed4bbecd"}},{"code_sha256_prefix":"b20a98cc74908419","entry":"attack","repo":"sizhe-chen/querynet","repo_kind":"official","path":"querynet.py","file_url":"https://github.com/sizhe-chen/querynet/blob/HEAD/querynet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b20a98cc74908419"}},{"code_sha256_prefix":"67992ec4b4e8206e","entry":"pseudo_gaussian_pert_rectangles","repo":"sizhe-chen/querynet","repo_kind":"official","path":"attacker.py","file_url":"https://github.com/sizhe-chen/querynet/blob/HEAD/attacker.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"67992ec4b4e8206e"}},{"code_sha256_prefix":"e185f97921f5be41","entry":"random_classes_except_current","repo":"allenchen1998/querynet","repo_kind":"official","path":"utils.py","file_url":"https://github.com/allenchen1998/querynet/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e185f97921f5be41"}},{"code_sha256_prefix":"8bf374c9e1999142","entry":"softmax","repo":"allenchen1998/querynet","repo_kind":"official","path":"utils.py","file_url":"https://github.com/allenchen1998/querynet/blob/HEAD/utils.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8bf374c9e1999142"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}