{"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/verifying-message-passing-neural-networks-via","title":"Verifying message-passing neural networks via topology-based bounds tightening","arxiv_id":"2402.13937","date":"2024-02-21","proceeding":null,"authors":["Christopher Hojny","Shiqiang Zhang","Juan S. Campos","Ruth Misener"],"abstract":"Since graph neural networks (GNNs) are often vulnerable to attack, we need to know when we can trust them. We develop a computationally effective approach towards providing robust certificates for message-passing neural networks (MPNNs) using a Rectified Linear Unit (ReLU) activation function. Because our work builds on mixed-integer optimization, it encodes a wide variety of subproblems, for example it admits (i) both adding and removing edges, (ii) both global and local budgets, and (iii) both topological perturbations and feature modifications. Our key technology, topology-based bounds tightening, uses graph structure to tighten bounds. We also experiment with aggressive bounds tightening to dynamically change the optimization constraints by tightening variable bounds. To demonstrate the effectiveness of these strategies, we implement an extension to the open-source branch-and-cut solver SCIP. We test on both node and graph classification problems and consider topological attacks that both add and remove edges.","url_abs":"https://arxiv.org/abs/2402.13937v2","url_pdf":"https://arxiv.org/pdf/2402.13937v2.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":"verifying-message-passing-neural-networks-via","repo_url":"https://github.com/christopherhojny/SCIP-MPNN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"graph-classification","task_name":"Graph Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.13937","atlas_url":"https://app.syntology.ai/?focus=2402.13937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13937"}},"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/christopherhojny/SCIP-MPNN","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"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":0,"samples":[{"code_sha256_prefix":"59d4faa2353bf6d7","entry":"get_n_layers","repo":"christopherhojny/SCIP-MPNN","repo_kind":"official","path":"scripts_experiments/generate_instance_from_json.py","file_url":"https://github.com/christopherhojny/SCIP-MPNN/blob/HEAD/scripts_experiments/generate_instance_from_json.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"59d4faa2353bf6d7"}},{"code_sha256_prefix":"7c1a2fa2a90a41de","entry":"get_target_graph","repo":"christopherhojny/SCIP-MPNN","repo_kind":"official","path":"scripts_experiments/generate_basic_instance_files_graphclassification.py","file_url":"https://github.com/christopherhojny/SCIP-MPNN/blob/HEAD/scripts_experiments/generate_basic_instance_files_graphclassification.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7c1a2fa2a90a41de"}},{"code_sha256_prefix":"559859c7b5c1f0bc","entry":"get_target_graph","repo":"christopherhojny/SCIP-MPNN","repo_kind":"official","path":"scripts_experiments/generate_basic_instance_files_nodeclassification.py","file_url":"https://github.com/christopherhojny/SCIP-MPNN/blob/HEAD/scripts_experiments/generate_basic_instance_files_nodeclassification.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"559859c7b5c1f0bc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}