{"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/a-unified-view-of-piecewise-linear-neural","title":"A Unified View of Piecewise Linear Neural Network Verification","arxiv_id":"1711.00455","date":"2017-11-01","proceeding":"NeurIPS 2018 12","authors":["Rudy Bunel","Ilker Turkaslan","Philip H. S. Torr","Pushmeet Kohli","M. Pawan Kumar"],"abstract":"The success of Deep Learning and its potential use in many safety-critical\napplications has motivated research on formal verification of Neural Network\n(NN) models. Despite the reputation of learned NN models to behave as black\nboxes and the theoretical hardness of proving their properties, researchers\nhave been successful in verifying some classes of models by exploiting their\npiecewise linear structure and taking insights from formal methods such as\nSatisifiability Modulo Theory. These methods are however still far from scaling\nto realistic neural networks. To facilitate progress on this crucial area, we\nmake two key contributions. First, we present a unified framework that\nencompasses previous methods. This analysis results in the identification of\nnew methods that combine the strengths of multiple existing approaches,\naccomplishing a speedup of two orders of magnitude compared to the previous\nstate of the art. Second, we propose a new data set of benchmarks which\nincludes a collection of previously released testcases. We use the benchmark to\nprovide the first experimental comparison of existing algorithms and identify\nthe factors impacting the hardness of verification problems.","url_abs":"http://arxiv.org/abs/1711.00455v3","url_pdf":"http://arxiv.org/pdf/1711.00455v3.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":"a-unified-view-of-piecewise-linear-neural","repo_url":"https://github.com/oval-group/PLNN-verification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-unified-view-of-piecewise-linear-neural","repo_url":"https://github.com/kaixiao/PLNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.00455","atlas_url":"https://app.syntology.ai/?focus=1711.00455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.00455"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/oval-group/PLNN-verification","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kaixiao/PLNN","reach":null}],"summary":{"ran_draft_wrong":6},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1},"listed":{"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":6,"samples":[{"code_sha256_prefix":"6280ca5b88086362","entry":"load_bench_results","repo":"oval-group/PLNN-verification","repo_kind":"official","path":"tools/compare_benchmarks.py","file_url":"https://github.com/oval-group/PLNN-verification/blob/HEAD/tools/compare_benchmarks.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":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"6280ca5b88086362"}},{"code_sha256_prefix":"f6e0770e78ef8a62","entry":"load_bench_results","repo":"kaixiao/PLNN","repo_kind":"listed","path":"tools/compare_benchmarks.py","file_url":"https://github.com/kaixiao/PLNN/blob/HEAD/tools/compare_benchmarks.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f6e0770e78ef8a62"}},{"code_sha256_prefix":"b7a2d9ed41e5556e","entry":"remove_fails","repo":"oval-group/PLNN-verification","repo_kind":"official","path":"tools/compare_benchmarks.py","file_url":"https://github.com/oval-group/PLNN-verification/blob/HEAD/tools/compare_benchmarks.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":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b7a2d9ed41e5556e"}},{"code_sha256_prefix":"0f083b406122c067","entry":"remove_fails","repo":"kaixiao/PLNN","repo_kind":"listed","path":"tools/compare_benchmarks.py","file_url":"https://github.com/kaixiao/PLNN/blob/HEAD/tools/compare_benchmarks.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0f083b406122c067"}},{"code_sha256_prefix":"0f31e6a5e99fa00d","entry":"remove_non_common","repo":"oval-group/PLNN-verification","repo_kind":"official","path":"tools/compare_benchmarks.py","file_url":"https://github.com/oval-group/PLNN-verification/blob/HEAD/tools/compare_benchmarks.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":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0f31e6a5e99fa00d"}},{"code_sha256_prefix":"459bdd0baac26180","entry":"remove_non_common","repo":"kaixiao/PLNN","repo_kind":"listed","path":"tools/compare_benchmarks.py","file_url":"https://github.com/kaixiao/PLNN/blob/HEAD/tools/compare_benchmarks.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"459bdd0baac26180"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}