{"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-power-of-abstention-and-data-driven-1","title":"An Analysis of Robustness of Non-Lipschitz Networks","arxiv_id":"2010.06154","date":"2020-10-13","proceeding":null,"authors":["Maria-Florina Balcan","Avrim Blum","Dravyansh Sharma","Hongyang Zhang"],"abstract":"Despite significant advances, deep networks remain highly susceptible to adversarial attack. One fundamental challenge is that small input perturbations can often produce large movements in the network's final-layer feature space. In this paper, we define an attack model that abstracts this challenge, to help understand its intrinsic properties. In our model, the adversary may move data an arbitrary distance in feature space but only in random low-dimensional subspaces. We prove such adversaries can be quite powerful: defeating any algorithm that must classify any input it is given. However, by allowing the algorithm to abstain on unusual inputs, we show such adversaries can be overcome when classes are reasonably well-separated in feature space. We further provide strong theoretical guarantees for setting algorithm parameters to optimize over accuracy-abstention trade-offs using data-driven methods. Our results provide new robustness guarantees for nearest-neighbor style algorithms, and also have application to contrastive learning, where we empirically demonstrate the ability of such algorithms to obtain high robust accuracy with low abstention rates. Our model is also motivated by strategic classification, where entities being classified aim to manipulate their observable features to produce a preferred classification, and we provide new insights into that area as well.","url_abs":"https://arxiv.org/abs/2010.06154v4","url_pdf":"https://arxiv.org/pdf/2010.06154v4.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-power-of-abstention-and-data-driven-1","repo_url":"https://github.com/dravyanshsharma/adversarial-contrastive","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"adversarial-defense","task_name":"Adversarial Defense"},{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"decision-making","task_name":"Decision Making"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.06154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.06154"}},"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/dravyanshsharma/adversarial-contrastive","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":2},"by_repo_kind":{"official":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"50768e5c6de22234","entry":"load_data","repo":"dravyanshsharma/adversarial-contrastive","repo_kind":"official","path":"n3_1__optimal_attack.py","file_url":"https://github.com/dravyanshsharma/adversarial-contrastive/blob/HEAD/n3_1__optimal_attack.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50768e5c6de22234"}},{"code_sha256_prefix":"14668e20fe120e68","entry":"make_rand_vector","repo":"dravyanshsharma/adversarial-contrastive","repo_kind":"official","path":"n3_1__optimal_attack.py","file_url":"https://github.com/dravyanshsharma/adversarial-contrastive/blob/HEAD/n3_1__optimal_attack.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"14668e20fe120e68"}},{"code_sha256_prefix":"d936aa6a51d78d60","entry":"rotation_matrix","repo":"dravyanshsharma/adversarial-contrastive","repo_kind":"official","path":"n3_1__optimal_attack.py","file_url":"https://github.com/dravyanshsharma/adversarial-contrastive/blob/HEAD/n3_1__optimal_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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d936aa6a51d78d60"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}