{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:08:44Z","timestamp":1782846524994,"version":"3.54.5"},"reference-count":78,"publisher":"Association for Computing Machinery (ACM)","issue":"FSE","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2422036"],"award-info":[{"award-number":["2422036"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2319131"],"award-info":[{"award-number":["2319131"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2238133"],"award-info":[{"award-number":["2238133"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Foundation","award":["2200621"],"award-info":[{"award-number":["2200621"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Softw. Eng."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>Neural network verification has emerged as a useful technique for improving the reliability of deep learning systems. Current verification approaches primarily focus on local robustness, where perturbations are applied independently to each input element. Despite its common use, local robustness does not capture perturbations that exhibit coordinated relationships between input elements. Such perturbations arise from systematic transformations or filtering operations that preserve structural characteristics of the data. These perturbations, which we call \u201cstructural robustness\u201d, represent a significant gap in existing verification capabilities.<\/jats:p>\n                  <jats:p>This work focuses on structural robustness verification by formalizing two important classes of structured perturbations: linear position-invariant and linear position-varying. Those perturbations allow input elements to be modified in coordinated ways while preserving essential data structure. The main challenge is that structural perturbations cannot be directly expressed using standard interval-based specification formats that existing verification tools typically support.<\/jats:p>\n                  <jats:p>To address this limitation, we introduce VeriS, a technique that reformulates structural robustness into standard local robustness problems by creating specialized subnetworks that encode perturbation behavior and integrate them with the original network architecture. VeriS enables verification across continuous spaces defined by structural robustness specifications while maintaining compatibility with existing verification tools. VeriS also introduces optimizations that significantly enhance verification performance such as converting complex operations into standard representations.<\/jats:p>\n                  <jats:p>We implement and evaluate VeriS on benchmarks involving neural networks across three domains: image classification, audio processing, and healthcare applications. Our evaluation, which encompasses 5508 verification problems, demonstrates that VeriS successfully verifies 78% of structural robustness specifications when integrated with state-of-the-art verification tools. These results show that VeriS enables the verification of complex structural perturbations that were previously beyond the reach of existing neural network verification.<\/jats:p>\n                  <jats:p>VeriS is available at: https:\/\/2.zoppoz.workers.dev:443\/https\/github.com\/dynaroars\/VeriS\/.<\/jats:p>","DOI":"10.1145\/3797095","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:06:14Z","timestamp":1782839174000},"page":"1492-1514","source":"Crossref","is-referenced-by-count":0,"title":["Verifying Structural Robustness of Deep Neural Network"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-3341-9794","authenticated-orcid":false,"given":"Hai","family":"Duong","sequence":"first","affiliation":[{"name":"George Mason University, Computer Science, Fairfax, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-4460-2225","authenticated-orcid":false,"given":"Thanh","family":"Le","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0003-0104-6166","authenticated-orcid":false,"given":"Lam","family":"Nguyen","sequence":"additional","affiliation":[{"name":"CMC Applied Technology Institute, Hanoi, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-4255-4592","authenticated-orcid":false,"given":"ThanhVu (Vu)","family":"Nguyen","sequence":"additional","affiliation":[{"name":"George Mason University, Computer Science, Fairfax, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-76384-8_2"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1605"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00134"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.19985"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2301.05815"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778775"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3660796"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.01541"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952190"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78122-3_7"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3576040"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-99991-8_14"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2307.10266"},{"key":"e_1_2_1_17_1","volume-title":"Dwyer","author":"Duong Hai","year":"2025","unstructured":"Hai Duong, ThanhVu Nguyen, and Matthew B. Dwyer. 2025. Generating and Checking DNN Verification Proofs. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. https:\/\/2.zoppoz.workers.dev:443\/https\/proceedings.neurips.cc\/paper_ files\/paper\/2025\/file\/5f326d2e040a20d52438873f5d727e58-Paper-Conference.pdf"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-"},{"key":"e_1_2_1_19_1","volume-title":"The Thirty-ninth Annual Conference on Neural Information Processing Systems. https: \/\/proceedings.neurips.cc\/paper_files\/paper\/2025\/file\/5ca2e240108d09e213859ea7ef2324bb-Paper-Conference.pdf","author":"Duong Hai","year":"2025","unstructured":"Hai Duong, David Shriver, ThanhVu Nguyen, and Matthew B Dwyer. 2025. Compositional neural network verification via assume-guarantee reasoning. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. https: \/\/proceedings.neurips.cc\/paper_files\/paper\/2025\/file\/5ca2e240108d09e213859ea7ef2324bb-Paper-Conference.pdf"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3643765"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68167-2_19"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851936"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.00263"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0426(2001)018<1749:"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6572"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414835"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3643678"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63387-9_1"},{"key":"e_1_2_1_30_1","unstructured":"The PhysioNet\/Computing in Cardiology Challenge. 2017. Cardiac Arrhythmia Dataset. https:\/\/2.zoppoz.workers.dev:443\/https\/physionet.org\/content\/ challenge-2017\/1.0.0\/"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-019-00619-1"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2986319"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1709.02802"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00108"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2510.26075"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2602.08801"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.08452"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3473131"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.06083"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1177\/074171367802800202"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268946"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21945-5"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","unstructured":"Mallek Mziou-Sallami and Faouzi Adjed. 2022. Towards a Certification of Deep Image Classifiers against Convolutional Attacks.. In ICAART (2). 419-428. doi:10.5220\/0010870400003116 10.5220\/0010870400003116","DOI":"10.5220\/0010870400003116"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1905.03828"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1080\/03772063"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-553180-1.X5000-5"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339576"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.252"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16352"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3078715"},{"key":"e_1_2_1_54_1","volume-title":"Fast and effective robustness certification. Advances in neural information processing systems 31","author":"Singh Gagandeep","year":"2018","unstructured":"Gagandeep Singh, Timon Gehr, Matthew Mirman, Markus P\u00fcschel, and Martin Vechev. 2018. Fast and effective robustness certification. Advances in neural information processing systems 31 (2018). https:\/\/2.zoppoz.workers.dev:443\/https\/proceedings.neurips.cc\/ paper_files\/paper\/2018\/file\/f2f446980d8e971ef3da97af089481c3-Paper.pdf"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290354"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-90870-6_5"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3358233"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6199"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34372-9"},{"key":"e_1_2_1_60_1","first-page":"1","article-title":"Tslearn, a machine learning toolkit for time series data","volume":"21","author":"Tavenard Romain","year":"2020","unstructured":"Romain Tavenard, Johann Faouzi, Gilles Vandewiele, Felix Divo, Guillaume Androz, Chester Holtz, Marie Payne, Roman Yurchak, Marc Ru\u00dfwurm, Kushal Kolar, et al. 2020. Tslearn, a machine learning toolkit for time series data. Journal of machine learning research 21, 118 (2020), 1-6. https:\/\/2.zoppoz.workers.dev:443\/http\/jmlr.org\/papers\/v21\/20-091.html","journal-title":"Journal of machine learning research"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00165-021-00553-4"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136817"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616266"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1809.08098"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.10829"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.06624"},{"key":"e_1_2_1_69_1","volume-title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition. ArXiv e-prints (April","author":"Warden P.","year":"2018","unstructured":"P. Warden. 2018. Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition. ArXiv e-prints (April 2018). arXiv:1804.03209 [cs.CL] https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/1804.03209"},{"key":"e_1_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2110.00476"},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-65630-9_13"},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-57256-2_2"},{"key":"e_1_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2002.12920"},{"key":"e_1_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2208.05740"},{"key":"e_1_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.00200"},{"key":"e_1_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2414429"},{"key":"e_1_2_1_77_1","volume-title":"Canonical time warping for alignment of human behavior. Advances in neural information processing systems 22","author":"Zhou Feng","year":"2009","unstructured":"Feng Zhou and Fernando Torre. 2009. Canonical time warping for alignment of human behavior. Advances in neural information processing systems 22 (2009). https:\/\/2.zoppoz.workers.dev:443\/https\/proceedings.neurips.cc\/paper_files\/paper\/2009\/file\/ 2ca65f58e35d9ad45bf7f3ae5cfd08f1-Paper.pdf"},{"key":"e_1_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460319.3464811"}],"container-title":["Proceedings of the ACM on Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/pdf\/10.1145\/3797095","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/pdf\/10.1145\/3797095","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:18:51Z","timestamp":1782843531000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/10.1145\/3797095"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":78,"journal-issue":{"issue":"FSE","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3797095"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3797095","relation":{},"ISSN":["2994-970X"],"issn-type":[{"value":"2994-970X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]}}}