{"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/general-cutting-planes-for-bound-propagation","title":"General Cutting Planes for Bound-Propagation-Based Neural Network Verification","arxiv_id":"2208.05740","date":"2022-08-11","proceeding":null,"authors":["huan zhang","Shiqi Wang","Kaidi Xu","Linyi Li","Bo Li","Suman Jana","Cho-Jui Hsieh","J. Zico Kolter"],"abstract":"Bound propagation methods, when combined with branch and bound, are among the most effective methods to formally verify properties of deep neural networks such as correctness, robustness, and safety. However, existing works cannot handle the general form of cutting plane constraints widely accepted in traditional solvers, which are crucial for strengthening verifiers with tightened convex relaxations. In this paper, we generalize the bound propagation procedure to allow the addition of arbitrary cutting plane constraints, including those involving relaxed integer variables that do not appear in existing bound propagation formulations. Our generalized bound propagation method, GCP-CROWN, opens up the opportunity to apply general cutting plane methods for neural network verification while benefiting from the efficiency and GPU acceleration of bound propagation methods. As a case study, we investigate the use of cutting planes generated by off-the-shelf mixed integer programming (MIP) solver. We find that MIP solvers can generate high-quality cutting planes for strengthening bound-propagation-based verifiers using our new formulation. Since the branching-focused bound propagation procedure and the cutting-plane-focused MIP solver can run in parallel utilizing different types of hardware (GPUs and CPUs), their combination can quickly explore a large number of branches with strong cutting planes, leading to strong verification performance. Experiments demonstrate that our method is the first verifier that can completely solve the oval20 benchmark and verify twice as many instances on the oval21 benchmark compared to the best tool in VNN-COMP 2021, and also noticeably outperforms state-of-the-art verifiers on a wide range of benchmarks. GCP-CROWN is part of the $\\alpha,\\!\\beta$-CROWN verifier, the VNN-COMP 2022 winner. Code is available at http://PaperCode.cc/GCP-CROWN","url_abs":"https://arxiv.org/abs/2208.05740v2","url_pdf":"https://arxiv.org/pdf/2208.05740v2.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":"general-cutting-planes-for-bound-propagation","repo_url":"https://github.com/huanzhang12/alpha-beta-CROWN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"general-cutting-planes-for-bound-propagation","repo_url":"https://github.com/Verified-Intelligence/alpha-beta-CROWN_vnncomp2024","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"general-cutting-planes-for-bound-propagation","repo_url":"https://github.com/avrahamraviv/formal-verification-of-object-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"general-cutting-planes-for-bound-propagation","repo_url":"https://github.com/lemutisme/biccos","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"general-cutting-planes-for-bound-propagation","repo_url":"https://github.com/verified-intelligence/alpha-beta-crown","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2208.05740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.05740"}},"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/lemutisme/biccos","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Verified-Intelligence/alpha-beta-CROWN_vnncomp2024","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/verified-intelligence/alpha-beta-crown","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huanzhang12/alpha-beta-CROWN","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/avrahamraviv/formal-verification-of-object-detection","reach":null}],"summary":{"ran":1,"ran_fixture":1,"unverified":4},"by_repo_kind":{"listed":{"samples":6,"ran":2,"repositories":2}},"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":6,"samples":[{"code_sha256_prefix":"6102b90c8a017444","entry":"ConfigHandler","repo":"avrahamraviv/formal-verification-of-object-detection","repo_kind":"listed","path":"complete_verifier/cuts/cut_verification.py","file_url":"https://github.com/avrahamraviv/formal-verification-of-object-detection/blob/HEAD/complete_verifier/cuts/cut_verification.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6102b90c8a017444"}},{"code_sha256_prefix":"226b29d234506943","entry":"patches_to_matrix","repo":"Verified-Intelligence/alpha-beta-CROWN_vnncomp2024","repo_kind":"listed","path":"complete_verifier/cuts/optimized_cuts.py","file_url":"https://github.com/Verified-Intelligence/alpha-beta-CROWN_vnncomp2024/blob/HEAD/complete_verifier/cuts/optimized_cuts.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"226b29d234506943"}},{"code_sha256_prefix":"e3423487e852c402","entry":"Cutter","repo":"Verified-Intelligence/alpha-beta-CROWN_vnncomp2024","repo_kind":"listed","path":"complete_verifier/cuts/optimized_cuts.py","file_url":"https://github.com/Verified-Intelligence/alpha-beta-CROWN_vnncomp2024/blob/HEAD/complete_verifier/cuts/optimized_cuts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e3423487e852c402"}},{"code_sha256_prefix":"fae7acb536120814","entry":"OptimizedCutter","repo":"Verified-Intelligence/alpha-beta-CROWN_vnncomp2024","repo_kind":"listed","path":"complete_verifier/cuts/optimized_cuts.py","file_url":"https://github.com/Verified-Intelligence/alpha-beta-CROWN_vnncomp2024/blob/HEAD/complete_verifier/cuts/optimized_cuts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"fae7acb536120814"}},{"code_sha256_prefix":"7901579aff6971d9","entry":"Patches","repo":"Verified-Intelligence/alpha-beta-CROWN_vnncomp2024","repo_kind":"listed","path":"complete_verifier/cuts/optimized_cuts.py","file_url":"https://github.com/Verified-Intelligence/alpha-beta-CROWN_vnncomp2024/blob/HEAD/complete_verifier/cuts/optimized_cuts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7901579aff6971d9"}},{"code_sha256_prefix":"48c660c22563df09","entry":"set_dependencies","repo":"avrahamraviv/formal-verification-of-object-detection","repo_kind":"listed","path":"complete_verifier/cuts/cut_verification.py","file_url":"https://github.com/avrahamraviv/formal-verification-of-object-detection/blob/HEAD/complete_verifier/cuts/cut_verification.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"48c660c22563df09"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}