{"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/improved-techniques-for-deterministic-l2","title":"Improved techniques for deterministic l2 robustness","arxiv_id":"2211.08453","date":"2022-11-15","proceeding":null,"authors":["Sahil Singla","Soheil Feizi"],"abstract":"Training convolutional neural networks (CNNs) with a strict 1-Lipschitz constraint under the $l_{2}$ norm is useful for adversarial robustness, interpretable gradients and stable training. 1-Lipschitz CNNs are usually designed by enforcing each layer to have an orthogonal Jacobian matrix (for all inputs) to prevent the gradients from vanishing during backpropagation. However, their performance often significantly lags behind that of heuristic methods to enforce Lipschitz constraints where the resulting CNN is not \\textit{provably} 1-Lipschitz. In this work, we reduce this gap by introducing (a) a procedure to certify robustness of 1-Lipschitz CNNs by replacing the last linear layer with a 1-hidden layer MLP that significantly improves their performance for both standard and provably robust accuracy, (b) a method to significantly reduce the training time per epoch for Skew Orthogonal Convolution (SOC) layers (>30\\% reduction for deeper networks) and (c) a class of pooling layers using the mathematical property that the $l_{2}$ distance of an input to a manifold is 1-Lipschitz. Using these methods, we significantly advance the state-of-the-art for standard and provable robust accuracies on CIFAR-10 (gains of +1.79\\% and +3.82\\%) and similarly on CIFAR-100 (+3.78\\% and +4.75\\%) across all networks. Code is available at \\url{https://github.com/singlasahil14/improved_l2_robustness}.","url_abs":"https://arxiv.org/abs/2211.08453v1","url_pdf":"https://arxiv.org/pdf/2211.08453v1.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":"improved-techniques-for-deterministic-l2","repo_url":"https://github.com/singlasahil14/improved_l2_robustness","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"linear-layer","method_name":"Linear Layer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.08453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.08453"}},"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":"deterministic:regex_extraction","url":"https://github.com/singlasahil14/improved_l2_robustness","reach":null}],"summary":{"ran":2,"ran_fixture":3,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":7,"samples":[{"code_sha256_prefix":"013b1bfe33f55f59","entry":"CRC_Full","repo":"singlasahil14/improved_l2_robustness","repo_kind":"official","path":"last_layers.py","file_url":"https://github.com/singlasahil14/improved_l2_robustness/blob/HEAD/last_layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"013b1bfe33f55f59"}},{"code_sha256_prefix":"f34004f7691b1cad","entry":"Softplus","repo":"singlasahil14/improved_l2_robustness","repo_kind":"official","path":"last_layers.py","file_url":"https://github.com/singlasahil14/improved_l2_robustness/blob/HEAD/last_layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f34004f7691b1cad"}},{"code_sha256_prefix":"26fcfa49bfa31422","entry":"bjorck_orthonormalize","repo":"singlasahil14/improved_l2_robustness","repo_kind":"official","path":"block_ortho_conv.py","file_url":"https://github.com/singlasahil14/improved_l2_robustness/blob/HEAD/block_ortho_conv.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":"26fcfa49bfa31422"}},{"code_sha256_prefix":"596e8fdbd9c6e7cf","entry":"power_iteration","repo":"singlasahil14/improved_l2_robustness","repo_kind":"official","path":"block_ortho_conv.py","file_url":"https://github.com/singlasahil14/improved_l2_robustness/blob/HEAD/block_ortho_conv.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"596e8fdbd9c6e7cf"}},{"code_sha256_prefix":"f5993577e4af0b97","entry":"topk_classes","repo":"singlasahil14/improved_l2_robustness","repo_kind":"official","path":"last_layers.py","file_url":"https://github.com/singlasahil14/improved_l2_robustness/blob/HEAD/last_layers.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f5993577e4af0b97"}},{"code_sha256_prefix":"fdef065e9e837d95","entry":"transpose_filter","repo":"singlasahil14/improved_l2_robustness","repo_kind":"official","path":"skew_ortho_conv.py","file_url":"https://github.com/singlasahil14/improved_l2_robustness/blob/HEAD/skew_ortho_conv.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fdef065e9e837d95"}},{"code_sha256_prefix":"296ca28a9ed825a8","entry":"orthogonal_matrix","repo":"singlasahil14/improved_l2_robustness","repo_kind":"official","path":"block_ortho_conv.py","file_url":"https://github.com/singlasahil14/improved_l2_robustness/blob/HEAD/block_ortho_conv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"296ca28a9ed825a8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}