{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/a-convex-relaxation-barrier-to-tight","title":"A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks","arxiv_id":"1902.08722","date":"2019-02-23","proceeding":"NeurIPS 2019 12","authors":["Hadi Salman","Greg Yang","huan zhang","Cho-Jui Hsieh","Pengchuan Zhang"],"abstract":"Verification of neural networks enables us to gauge their robustness against adversarial attacks. Verification algorithms fall into two categories: exact verifiers that run in exponential time and relaxed verifiers that are efficient but incomplete. In this paper, we unify all existing LP-relaxed verifiers, to the best of our knowledge, under a general convex relaxation framework. This framework works for neural networks with diverse architectures and nonlinearities and covers both primal and dual views of robustness verification. We further prove strong duality between the primal and dual problems under very mild conditions. Next, we perform large-scale experiments, amounting to more than 22 CPU-years, to obtain exact solution to the convex-relaxed problem that is optimal within our framework for ReLU networks. We find the exact solution does not significantly improve upon the gap between PGD and existing relaxed verifiers for various networks trained normally or robustly on MNIST and CIFAR datasets. Our results suggest there is an inherent barrier to tight verification for the large class of methods captured by our framework. We discuss possible causes of this barrier and potential future directions for bypassing it. Our code and trained models are available at http://github.com/Hadisalman/robust-verify-benchmark .","url_abs":"https://arxiv.org/abs/1902.08722v5","url_pdf":"https://arxiv.org/pdf/1902.08722v5.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-convex-relaxation-barrier-to-tight","repo_url":"https://github.com/Hadisalman/robust-verify-benchmark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-convex-relaxation-barrier-to-tight","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":"a-convex-relaxation-barrier-to-tight","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":"a-convex-relaxation-barrier-to-tight","repo_url":"https://github.com/huanzhang12/alpha-beta-CROWN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"a-convex-relaxation-barrier-to-tight","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":"CPU"}],"methods":[{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1902.08722","atlas_url":"https://app.syntology.ai/?focus=1902.08722","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1902.08722"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1902.08722\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1902.08722"},"call":"get_concepts_for_paper(arxiv_id=\"1902.08722\")"}],"by_repo":[{"repo":"Hadisalman/robust-verify-benchmark","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1711.00851"],"harvested_for_calls":[{"arxiv_id":"1711.00851","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1711.00851"},"call":"get_harvested_code_for_paper(arxiv_id=\"1711.00851\")"}]},{"repo":"Verified-Intelligence/alpha-beta-CROWN_vnncomp2024","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["2011.13824","2103.06624","2208.05740","2405.21063"],"harvested_for_calls":[{"arxiv_id":"2011.13824","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2011.13824"},"call":"get_harvested_code_for_paper(arxiv_id=\"2011.13824\")"},{"arxiv_id":"2103.06624","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.06624"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.06624\")"},{"arxiv_id":"2208.05740","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2208.05740"},"call":"get_harvested_code_for_paper(arxiv_id=\"2208.05740\")"},{"arxiv_id":"2405.21063","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2405.21063"},"call":"get_harvested_code_for_paper(arxiv_id=\"2405.21063\")"}]},{"repo":"avrahamraviv/formal-verification-of-object-detection","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2208.05740"],"harvested_for_calls":[{"arxiv_id":"2208.05740","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2208.05740"},"call":"get_harvested_code_for_paper(arxiv_id=\"2208.05740\")"}]},{"repo":"huanzhang12/alpha-beta-CROWN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2405.21063"],"harvested_for_calls":[{"arxiv_id":"2405.21063","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2405.21063"},"call":"get_harvested_code_for_paper(arxiv_id=\"2405.21063\")"}]},{"repo":"verified-intelligence/alpha-beta-crown","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"dbcd40130835db2b9f3acff4ce092a611ff936fe1a9de8b5caba2bafd45e9949","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}