{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T20:53:23Z","timestamp":1760043203838,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Opening Project of Shanghai Trusted Industrial Control Platform"},{"name":"National Nature Science Foundation of China","award":["61972150"],"award-info":[{"award-number":["61972150"]}]},{"name":"Fundamental Research Funds for Central Universities"},{"name":"National Key Research and Development","award":["2019YFA0706404"],"award-info":[{"award-number":["2019YFA0706404"]}]},{"name":"NSFC-ISF Joint Program","award":["62161146001,3420\/21"],"award-info":[{"award-number":["62161146001,3420\/21"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3551349.3556907","type":"proceedings-article","created":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T20:43:54Z","timestamp":1672951434000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Provably Tightest Linear Approximation for Robustness Verification of Sigmoid-like Neural Networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0230-0301","authenticated-orcid":false,"given":"Zhaodi","family":"Zhang","sequence":"first","affiliation":[{"name":"East China Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8517-4100","authenticated-orcid":false,"given":"Yiting","family":"Wu","sequence":"additional","affiliation":[{"name":"East China Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3578-7432","authenticated-orcid":false,"given":"Si","family":"Liu","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5347-8281","authenticated-orcid":false,"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"East China Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1938-2902","authenticated-orcid":false,"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"East China Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,1,5]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2752459"},{"key":"e_1_3_2_1_2_1","unstructured":"aptx4869tjx. 2021. Pretrained Models. https:\/\/github.com\/aptx4869tjx\/train_network."},{"volume-title":"Principles of model checking","author":"Baier Christel","key":"e_1_3_2_1_3_1","unstructured":"Christel Baier and Joost-Pieter Katoen. 2008. Principles of model checking. MIT press."},{"key":"e_1_3_2_1_4_1","volume-title":"Scalable Quantitative Verification For Deep Neural Networks. In 43rd IEEE\/ACM International Conference on Software Engineering, ICSE 2021","author":"Baluta Teodora","year":"2021","unstructured":"Teodora Baluta, Zheng\u00a0Leong Chua, Kuldeep\u00a0S. Meel, and Prateek Saxena. 2021. Scalable Quantitative Verification For Deep Neural Networks. In 43rd IEEE\/ACM International Conference on Software Engineering, ICSE 2021, Madrid, Spain, 22-30 May 2021. IEEE, 312\u2013323."},{"key":"e_1_3_2_1_5_1","volume-title":"CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks. In AAAI Conference on Artificial Intelligence (AAAI). 3240\u20133247","author":"Boopathy Akhilan","year":"2019","unstructured":"Akhilan Boopathy, Tsui-Wei Weng, Pin-Yu Chen, Sijia Liu, and Luca Daniel. 2019. CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks. In AAAI Conference on Artificial Intelligence (AAAI). 3240\u20133247."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5729"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3375894.3375898"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0058022"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1137\/19M1272780"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/512950.512973"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460319.3464801"},{"key":"e_1_3_2_1_13_1","volume-title":"Output Range Analysis for Deep Feedforward Neural Networks. In NASA Formal Methods Symposium (NFM). Springer, 121\u2013138","author":"Dutta Souradeep","year":"2018","unstructured":"Souradeep Dutta, Susmit Jha, Sriram Sankaranarayanan, and Ashish Tiwari. 2018. Output Range Analysis for Deep Feedforward Neural Networks. In NASA Formal Methods Symposium (NFM). Springer, 121\u2013138."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68167-2_19"},{"key":"e_1_3_2_1_15_1","unstructured":"William Fleshman Edward Raff Jared Sylvester 2018. Non-Negative Networks Against Adversarial Attacks. CoRR abs\/1806.06108(2018). http:\/\/arxiv.org\/abs\/1806.06108"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2018.00058"},{"key":"e_1_3_2_1_17_1","unstructured":"Saad\u00a0Hikmat Haji and Adnan\u00a0Mohsin Abdulazeez. 2021. Comparison of optimization techniques based on gradient descent algorithm: A review. PalArch\u2019s Journal of Archaeology of Egypt\/Egyptology 18 4(2021) 2715\u20132743."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA200385"},{"key":"e_1_3_2_1_19_1","unstructured":"Omid Kargarnovin Amir\u00a0Mahdi Sadeghzadeh and Rasool Jalili. 2021. Mal2GCN: A Robust Malware Detection Approach Using Deep Graph Convolutional Networks With Non-Negative Weights. arXiv preprint arXiv:2108.12473(2021)."},{"key":"e_1_3_2_1_20_1","volume-title":"Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks. In International Conference on Computer Aided Verification (CAV). Springer, 97\u2013117","author":"Katz Guy","year":"2017","unstructured":"Guy Katz, Clark Barrett, David\u00a0L Dill, Kyle Julian, and Mykel\u00a0J Kochenderfer. 2017. Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks. In International Conference on Computer Aided Verification (CAV). Springer, 97\u2013117."},{"key":"e_1_3_2_1_21_1","unstructured":"Alex Krizhevsky Geoffrey Hinton 2009. Learning Multiple Layers of Features from Tiny Images. (2009)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_25_1","volume-title":"Annual Conference on Neural Information Processing Systems (NeurIPS) 33","author":"Lee Sungyoon","year":"2020","unstructured":"Sungyoon Lee, Jaewook Lee, and Saerom Park. 2020. Lipschitz-certifiable training with a tight outer bound. Annual Conference on Neural Information Processing Systems (NeurIPS) 33 (2020), 16891\u201316902."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01168"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_28_1","volume-title":"Fastened CROWN: Tightened Neural Network Robustness Certificates. In AAAI Conference on Artificial Intelligence (AAAI). 5037\u20135044","author":"Lyu Zhaoyang","year":"2020","unstructured":"Zhaoyang Lyu, Ching-Yun Ko, Zhifeng Kong, Ngai Wong, Dahua Lin, and Luca Daniel. 2020. Fastened CROWN: Tightened Neural Network Robustness Certificates. In AAAI Conference on Artificial Intelligence (AAAI). 5037\u20135044."},{"key":"e_1_3_2_1_29_1","volume-title":"Accuracy-Robustness Trade-Off for Positively Weighted Neural Networks. In International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 8389\u20138393","author":"Neacsu Ana","year":"2020","unstructured":"Ana Neacsu, Jean-Christophe Pesquet, and Corneliu Burileanu. 2020. Accuracy-Robustness Trade-Off for Positively Weighted Neural Networks. In International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 8389\u20138393."},{"key":"e_1_3_2_1_30_1","volume-title":"Fully Convolutional Neural Networks with Full-Scale-Features for Semantic Segmentation. In AAAI Conference on Artificial Intelligence (AAAI). AAAI Press, 4240\u20134246","author":"Pan Tianxiang","year":"2017","unstructured":"Tianxiang Pan, Bin Wang, Guiguang Ding, and Jun-Hai Yong. 2017. Fully Convolutional Neural Networks with Full-Scale-Features for Semantic Segmentation. In AAAI Conference on Artificial Intelligence (AAAI). AAAI Press, 4240\u20134246."},{"key":"e_1_3_2_1_31_1","first-page":"273","article-title":"Non-convex Optimization Using Parameter Continuation Methods for Deep Neural Networks","volume":"2","author":"Pathak Harsh\u00a0Nilesh","year":"2020","unstructured":"Harsh\u00a0Nilesh Pathak and Randy\u00a0Clinton Paffenroth. 2020. Non-convex Optimization Using Parameter Continuation Methods for Deep Neural Networks. Deep Learning Applications, Volume 2 1232 (2020), 273\u2013298.","journal-title":"Deep Learning Applications"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416560"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14295-6_24"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/368"},{"key":"e_1_3_2_1_36_1","volume-title":"Annual Conference on Neural Information Processing Systems (NeurIPS). 9832\u20139842","author":"Salman Hadi","year":"2019","unstructured":"Hadi Salman, Greg Yang, Huan Zhang, Cho-Jui Hsieh, and Pengchuan Zhang. 2019. A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks. In Annual Conference on Neural Information Processing Systems (NeurIPS). 9832\u20139842."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Marco S\u00e4lzer and Martin Lange. 2021. Reachability Is NP-Complete Even for the Simplest Neural Networks. CoRR abs\/2108.13179(2021).","DOI":"10.1007\/978-3-030-89716-1_10"},{"key":"e_1_3_2_1_38_1","volume-title":"Beyond the Single Neuron Convex Barrier for Neural Network Certification. In Annual Conference on Neural Information Processing Systems (NeurIPS). 15072\u201315083","author":"Singh Gagandeep","year":"2019","unstructured":"Gagandeep Singh, Rupanshu Ganvir, Markus P\u00fcschel, and Martin\u00a0T. Vechev. 2019. Beyond the Single Neuron Convex Barrier for Neural Network Certification. In Annual Conference on Neural Information Processing Systems (NeurIPS). 15072\u201315083."},{"key":"e_1_3_2_1_39_1","unstructured":"Gagandeep Singh Timon Gehr Matthew Mirman Markus P\u00fcschel and Martin\u00a0T Vechev. 2018. Fast and Effective Robustness Certification.. In Advances in Neural Information Processing Systems (NeurIPS). 10825\u201310836."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290354"},{"key":"e_1_3_2_1_41_1","volume-title":"Revisited: Tightened Single-Neuron Relaxations for Neural Network Verification. In Annual Conference on Neural Information Processing Systems (NeurIPS).","author":"Tjandraatmadja Christian","year":"2020","unstructured":"Christian Tjandraatmadja, Ross Anderson, Joey Huchette, Will Ma, Krunal Patel, and Juan\u00a0Pablo Vielma. 2020. The Convex Relaxation Barrier, Revisited: Tightened Single-Neuron Relaxations for Neural Network Verification. In Annual Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_42_1","volume-title":"Evaluating Robustness of Neural Networks with Mixed Integer Programming. In International Conference on Learning Representations (ICLR).","author":"Tjeng Vincent","year":"2019","unstructured":"Vincent Tjeng, Kai Xiao, and Russ Tedrake. 2019. Evaluating Robustness of Neural Networks with Mixed Integer Programming. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-53288-8_1"},{"key":"e_1_3_2_1_45_1","volume-title":"Annual Conference on Neural Information Processing Systems (NeurIPS). 6369\u20136379","author":"Wang Shiqi","year":"2018","unstructured":"Shiqi Wang, Kexin Pei, Justin Whitehouse, Junfeng Yang, and Suman Jana. 2018. Efficient formal safety analysis of neural networks. In Annual Conference on Neural Information Processing Systems (NeurIPS). 6369\u20136379."},{"key":"e_1_3_2_1_46_1","volume-title":"USENIX Security Symposium (USENIX Security). 1599\u20131614","author":"Wang Shiqi","year":"2018","unstructured":"Shiqi Wang, Kexin Pei, Justin Whitehouse, Junfeng Yang, and Suman Jana. 2018. Formal Security Analysis of Neural Networks using Symbolic Intervals. In USENIX Security Symposium (USENIX Security). 1599\u20131614."},{"key":"e_1_3_2_1_47_1","volume-title":"Annual Conference on Neural Information Processing Systems (NeurIPS) 34","author":"Wang Shiqi","year":"2021","unstructured":"Shiqi Wang, Huan Zhang, Kaidi Xu, Xue Lin, Suman Jana, Cho-Jui Hsieh, and J\u00a0Zico Kolter. 2021. Beta-crown: Efficient bound propagation with per-neuron split constraints for neural network robustness verification. Annual Conference on Neural Information Processing Systems (NeurIPS) 34 (2021)."},{"key":"e_1_3_2_1_48_1","volume-title":"Towards Fast Computation of Certified Robustness for ReLU Networks. In International Conference on Machine Learning (ICML). PMLR, 5276\u20135285","author":"Weng Lily","year":"2018","unstructured":"Lily Weng, Huan Zhang, Hongge Chen, Zhao Song, 2018. Towards Fast Computation of Certified Robustness for ReLU Networks. In International Conference on Machine Learning (ICML). PMLR, 5276\u20135285."},{"key":"e_1_3_2_1_49_1","volume-title":"Towards Fast Computation of Certified Robustness for ReLU Networks. In International Conference on Machine LearningICML, Vol.\u00a080","author":"Weng Tsui-Wei","year":"2018","unstructured":"Tsui-Wei Weng, Huan Zhang, Hongge Chen, Zhao Song, 2018. Towards Fast Computation of Certified Robustness for ReLU Networks. In International Conference on Machine LearningICML, Vol.\u00a080. PMLR, 5273\u20135282."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448248"},{"key":"e_1_3_2_1_51_1","volume-title":"Tightening Robustness Verification of Convolutional Neural Networks with Fine-Grained Linear Approximation. In AAAI Conference on Artificial Intelligence (AAAI). 11674\u201311681","author":"Wu Yiting","year":"2021","unstructured":"Yiting Wu and Min Zhang. 2021. Tightening Robustness Verification of Convolutional Neural Networks with Fine-Grained Linear Approximation. In AAAI Conference on Artificial Intelligence (AAAI). 11674\u201311681."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2808470"},{"key":"e_1_3_2_1_53_1","unstructured":"Han Xiao Kashif Rasul and Roland Vollgraf. 2017. Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms. CoRR abs\/1708.07747(2017)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468612"},{"key":"e_1_3_2_1_55_1","volume-title":"Efficient Neural Network Robustness Certification with General Activation Functions. In Annual Conference on Neural Information Processing Systems (NeurIPS). 4944\u20134953","author":"Zhang Huan","year":"2018","unstructured":"Huan Zhang, Tsui-Wei Weng, Pin-Yu Chen, Cho-Jui Hsieh, and Luca Daniel. 2018. Efficient Neural Network Robustness Certification with General Activation Functions. In Annual Conference on Neural Information Processing Systems (NeurIPS). 4944\u20134953."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"crossref","unstructured":"Zhaodi Zhang Yitinh Wu Si Liu Jing Liu and Min Zhang. 2022. Provably Tightest Linear Approximation for Robustness Verification of Sigmoid-like Neural Networks. Technical Report. https:\/\/arxiv.org\/abs\/2208.09872","DOI":"10.1145\/3551349.3556907"}],"event":{"name":"ASE '22: 37th IEEE\/ACM International Conference on Automated Software Engineering","acronym":"ASE '22","location":"Rochester MI USA"},"container-title":["Proceedings of the 37th IEEE\/ACM International Conference on Automated Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3551349.3556907","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3551349.3556907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T07:53:34Z","timestamp":1755849214000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3551349.3556907"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":56,"alternative-id":["10.1145\/3551349.3556907","10.1145\/3551349"],"URL":"https:\/\/doi.org\/10.1145\/3551349.3556907","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2023-01-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}