{"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/on-the-robustness-of-deep-k-nearest-neighbors","title":"On the Robustness of Deep K-Nearest Neighbors","arxiv_id":"1903.08333","date":"2019-03-20","proceeding":null,"authors":["Chawin Sitawarin","David Wagner"],"abstract":"Despite a large amount of attention on adversarial examples, very few works\nhave demonstrated an effective defense against this threat. We examine Deep\nk-Nearest Neighbor (DkNN), a proposed defense that combines k-Nearest Neighbor\n(kNN) and deep learning to improve the model's robustness to adversarial\nexamples. It is challenging to evaluate the robustness of this scheme due to a\nlack of efficient algorithm for attacking kNN classifiers with large k and\nhigh-dimensional data. We propose a heuristic attack that allows us to use\ngradient descent to find adversarial examples for kNN classifiers, and then\napply it to attack the DkNN defense as well. Results suggest that our attack is\nmoderately stronger than any naive attack on kNN and significantly outperforms\nother attacks on DkNN.","url_abs":"http://arxiv.org/abs/1903.08333v1","url_pdf":"http://arxiv.org/pdf/1903.08333v1.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":"on-the-robustness-of-deep-k-nearest-neighbors","repo_url":"https://github.com/chawins/knn-defense","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"on-the-robustness-of-deep-k-nearest-neighbors","repo_url":"https://github.com/fiona-lxd/AdvKnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.08333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.08333"}},"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/chawins/knn-defense","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fiona-lxd/AdvKnn","reach":null}],"summary":{"ran_draft_wrong":1,"ran_fixture":2},"by_repo_kind":{},"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":"26d9f9fc3682e736","entry":"get_feats","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"26d9f9fc3682e736"}},{"code_sha256_prefix":"9327cee9ffcdcc5f","entry":"knn","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"9327cee9ffcdcc5f"}},{"code_sha256_prefix":"79c0d47a0e121164","entry":"perturb","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"79c0d47a0e121164"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}