{"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/efficient-certified-training-and-robustness","title":"Efficient Certified Training and Robustness Verification of Neural ODEs","arxiv_id":"2303.05246","date":"2023-03-09","proceeding":null,"authors":["Mustafa Zeqiri","Mark Niklas Müller","Marc Fischer","Martin Vechev"],"abstract":"Neural Ordinary Differential Equations (NODEs) are a novel neural architecture, built around initial value problems with learned dynamics which are solved during inference. Thought to be inherently more robust against adversarial perturbations, they were recently shown to be vulnerable to strong adversarial attacks, highlighting the need for formal guarantees. However, despite significant progress in robustness verification for standard feed-forward architectures, the verification of high dimensional NODEs remains an open problem. In this work, we address this challenge and propose GAINS, an analysis framework for NODEs combining three key ideas: (i) a novel class of ODE solvers, based on variable but discrete time steps, (ii) an efficient graph representation of solver trajectories, and (iii) a novel abstraction algorithm operating on this graph representation. Together, these advances enable the efficient analysis and certified training of high-dimensional NODEs, by reducing the runtime from an intractable $O(\\exp(d)+\\exp(T))$ to ${O}(d+T^2 \\log^2T)$ in the dimensionality $d$ and integration time $T$. In an extensive evaluation on computer vision (MNIST and FMNIST) and time-series forecasting (PHYSIO-NET) problems, we demonstrate the effectiveness of both our certified training and verification methods.","url_abs":"https://arxiv.org/abs/2303.05246v1","url_pdf":"https://arxiv.org/pdf/2303.05246v1.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":"efficient-certified-training-and-robustness","repo_url":"https://github.com/eth-sri/gains","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"time-series-forecasting","task_name":"Time Series Forecasting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.05246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.05246"}},"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/eth-sri/gains","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"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":"41811cef554cd46c","entry":"PGD_bounds","repo":"eth-sri/gains","repo_kind":"official","path":"bounds.py","file_url":"https://github.com/eth-sri/gains/blob/HEAD/bounds.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"41811cef554cd46c"}},{"code_sha256_prefix":"d0720b8421e0c923","entry":"compute_masked_likelihood","repo":"eth-sri/gains","repo_kind":"official","path":"latent_attack_MAE.py","file_url":"https://github.com/eth-sri/gains/blob/HEAD/latent_attack_MAE.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d0720b8421e0c923"}},{"code_sha256_prefix":"a4301686bb4faaa1","entry":"contained","repo":"eth-sri/gains","repo_kind":"official","path":"gains_exp.py","file_url":"https://github.com/eth-sri/gains/blob/HEAD/gains_exp.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4301686bb4faaa1"}},{"code_sha256_prefix":"5b1337f672e212f6","entry":"gaussian_log_likelihood","repo":"eth-sri/gains","repo_kind":"official","path":"latent_attack_MAE.py","file_url":"https://github.com/eth-sri/gains/blob/HEAD/latent_attack_MAE.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5b1337f672e212f6"}},{"code_sha256_prefix":"5a74f6ba69bffc31","entry":"norm","repo":"eth-sri/gains","repo_kind":"official","path":"model.py","file_url":"https://github.com/eth-sri/gains/blob/HEAD/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a74f6ba69bffc31"}},{"code_sha256_prefix":"a1b63adde92dd989","entry":"norm_LN","repo":"eth-sri/gains","repo_kind":"official","path":"model.py","file_url":"https://github.com/eth-sri/gains/blob/HEAD/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a1b63adde92dd989"}},{"code_sha256_prefix":"132869b5387d420e","entry":"split_last_dim","repo":"eth-sri/gains","repo_kind":"official","path":"latent_model.py","file_url":"https://github.com/eth-sri/gains/blob/HEAD/latent_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"132869b5387d420e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}