{"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/deepsplit-scalable-verification-of-deep","title":"DeepSplit: Scalable Verification of Deep Neural Networks via Operator Splitting","arxiv_id":"2106.09117","date":"2021-06-16","proceeding":null,"authors":["Shaoru Chen","Eric Wong","J. Zico Kolter","Mahyar Fazlyab"],"abstract":"Analyzing the worst-case performance of deep neural networks against input perturbations amounts to solving a large-scale non-convex optimization problem, for which several past works have proposed convex relaxations as a promising alternative. However, even for reasonably-sized neural networks, these relaxations are not tractable, and so must be replaced by even weaker relaxations in practice. In this work, we propose a novel operator splitting method that can directly solve a convex relaxation of the problem to high accuracy, by splitting it into smaller sub-problems that often have analytical solutions. The method is modular, scales to very large problem instances, and compromises operations that are amenable to fast parallelization with GPU acceleration. We demonstrate our method in bounding the worst-case performance of large convolutional networks in image classification and reinforcement learning settings, and in reachability analysis of neural network dynamical systems.","url_abs":"https://arxiv.org/abs/2106.09117v3","url_pdf":"https://arxiv.org/pdf/2106.09117v3.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":"deepsplit-scalable-verification-of-deep","repo_url":"https://github.com/shaoruchen/deepsplit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.09117","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09117"}},"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/shaoruchen/deepsplit","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"0828f3916e8e1c25","entry":"relu_proj_convex_hull","repo":"shaoruchen/deepsplit","repo_kind":"official","path":"DeepSplit/ADMM.py","file_url":"https://github.com/shaoruchen/deepsplit/blob/HEAD/DeepSplit/ADMM.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":"0828f3916e8e1c25"}},{"code_sha256_prefix":"97f0c65182eb6a9a","entry":"relu_projection","repo":"shaoruchen/deepsplit","repo_kind":"official","path":"DeepSplit/ADMM.py","file_url":"https://github.com/shaoruchen/deepsplit/blob/HEAD/DeepSplit/ADMM.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":"97f0c65182eb6a9a"}},{"code_sha256_prefix":"00fdeb0dcb2b325f","entry":"init_sequential_admm_session","repo":"shaoruchen/deepsplit","repo_kind":"official","path":"DeepSplit/ADMM.py","file_url":"https://github.com/shaoruchen/deepsplit/blob/HEAD/DeepSplit/ADMM.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"00fdeb0dcb2b325f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}