{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T07:32:32Z","timestamp":1780644752240,"version":"3.54.1"},"reference-count":106,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100002427","name":"Ford Motor Company","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002427","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,14]]},"DOI":"10.1109\/cdc45484.2021.9683154","type":"proceedings-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T20:50:18Z","timestamp":1643748618000},"page":"6326-6340","source":"Crossref","is-referenced-by-count":7,"title":["Neural Network Verification in Control"],"prefix":"10.1109","author":[{"given":"Michael","family":"Everett","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref38","first-page":"1071","article-title":"Learning neural network policies with guided policy search under unknown dynamics","volume":"27","author":"levine","year":"2014","journal-title":"NIPS"},{"key":"ref33","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref32","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref31","article-title":"Stella: a multiplatform atari 2600 vcs emulator","author":"mott","year":"1995"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref37","article-title":"Alvinn: An autonomous land vehicle in a neural network","author":"pomerleau","year":"1989","journal-title":"CARNEGIE-MELLON UNIV PITTSBURGH PA ARTIFICIAL INTELLIGENCE AND PSYCHOLOGY PROJECT"},{"key":"ref36","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref35","article-title":"Recent advances´ in autoencoder-based representation learning","author":"tschannen","year":"2018","journal-title":"NeurIPS Workshop on Bayesian Deep Learning (NeurIPS BDL)"},{"key":"ref34","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"NIPS"},{"key":"ref28","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019"},{"key":"ref27","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"12th USENIX Symposium on Operating Systems Design and Implementation ( OSDI 16)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.1989.4790360"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-46466-9_18"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4939.003.0009","article-title":"Adaptive control using neural networks","volume":"3","author":"narendra","year":"1991","journal-title":"Neural Networks for Control"},{"key":"ref24","author":"sanders","year":"2010","journal-title":"CUDA by Example An Introduction to General-Purpose GPU Programming"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029310"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref100","article-title":"Fast neural network verification via shadow prices","author":"rubies-royo","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref50","first-page":"1","article-title":"Learning lyapunov functions for hybrid systems","author":"chen","year":"2021","journal-title":"Proceedings of the 24th International Conference on Hybrid Systems Computation and Control"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3342355"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-46681-0_5"},{"key":"ref58","article-title":"An introduction to cora 2015","author":"althoff","year":"2015","journal-title":"Proc of the Workshop on Applied Verification for Continuous and Hybrid Systems"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39799-8_18"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-22110-1_30"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/5.871303"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2015.2496293"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-0224-5"},{"key":"ref52","volume":"67","author":"garoche","year":"2019","journal-title":"Formal Verification of Control Software"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8263977"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-62416-7_19"},{"key":"ref3","article-title":"Adversarial attacks on neural network policies","author":"huang","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206245"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053342"},{"key":"ref8","first-page":"700","article-title":"Domain randomization for simulation-based policy optimization with transferability assessment","author":"muratore","year":"2018","journal-title":"2nd Annual conference on Robot Learning CoRL 2018 Zürich Switzerland 29 - 31 October 2018 Proceedings"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561949"},{"key":"ref7","article-title":"Epopt: Learning robust neural network policies using model ensembles","author":"rajeswaran","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref9","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"2017","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341797"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.871854"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8815339"},{"key":"ref47","article-title":"Generation of lyapunov functions by neural networks","volume":"2008","author":"noroozi","year":"2008","journal-title":"Proceedings of the World Congress on Engineering"},{"key":"ref42","article-title":"Lagrangian neural networks","author":"cranmer","year":"2020","journal-title":"ICLR 2020 Workshop on Integration of Deep Neural Models and Differential Equations"},{"key":"ref41","article-title":"Deep lagrangian networks: Using physics as model prior for deep learning","author":"lutter","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-55125\/v1","article-title":"Universal differential equations for scientific machine learning","author":"rackauckas","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.10.045"},{"key":"ref73","first-page":"5283","article-title":"Provable defenses against adversarial examples via the convex outer adversarial polytope","author":"wong","year":"2018","journal-title":"ICML vol 80 of Proceedings of Machine Learning Research"},{"key":"ref72","first-page":"4939","article-title":"Efficient neural network robustness certification with general activation functions","author":"zhang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref71","first-page":"10802","article-title":"Fast and effective robustness certification","author":"singh","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref70","article-title":"Towards fast computation of certified robustness for relu networks","author":"weng","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref76","article-title":"Automatic perturbation analysis for scalable certified robustness and beyond","volume":"33","author":"xu","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/MDAT.2020.3015712"},{"key":"ref74","article-title":"Certified defenses against adversarial examples","author":"raghunathan","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref75","article-title":"Safety verification and robustness analysis of neural networks via quadratic constraints and semidefinite programming","author":"fazlyab","year":"2020","journal-title":"IEEE Transactions on Automatic Control"},{"key":"ref78","article-title":"Verification for machine learning, autonomy, and neural networks survey","author":"xiang","year":"2018"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/72.501721"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-41528-4_29"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2002.1184414"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68167-2_19"},{"key":"ref64","first-page":"97","article-title":"Reluplex: An efficient SMT solver for verifying deep neural networks","author":"katz","year":"0"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63387-9_1"},{"key":"ref66","article-title":"An approach to reachability analysis for feed-forward relu neural networks","author":"lomuscio","year":"2017","journal-title":"CoRR"},{"key":"ref67","article-title":"Evaluating robustness of neural networks with mixed integer programming","author":"tjeng","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2018.00058"},{"key":"ref2","article-title":"Intriguing properties of neural networks","author":"szegedy","year":"2014","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref69","article-title":"On the effectiveness of interval bound propagation for training verifiably robust models","author":"gowal","year":"2018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2017.04.001"},{"key":"ref95","article-title":"The convex relaxation barrier, revisited: Tightened single-neuron relaxations for neural network verification","volume":"33","author":"tjandraatmadja","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref94","first-page":"15098","article-title":"Beyond the single neuron convex barrier for neural network certification","author":"singh","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref93","first-page":"5318","article-title":"Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming","volume":"33","author":"dathathri","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref106","article-title":"Soft actor-critic for discrete action settings","author":"christodoulou","year":"2019"},{"key":"ref92","first-page":"5276","article-title":"Towards fast computation of certified robustness for relu networks","author":"weng","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref105","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0"},{"key":"ref91","first-page":"97","article-title":"Reluplex: An efficient smt solver for verifying deep neural networks","author":"katz","year":"2017","journal-title":"International Conference on Computer Aided Verification"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3111139"},{"key":"ref90","first-page":"9835","article-title":"A convex relaxation barrier to tight robustness verification of neural networks","author":"salman","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref103","doi-asserted-by":"crossref","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref102","first-page":"2909","article-title":"Cvxpy: A python-embedded modeling language for convex optimization","volume":"17","author":"diamond","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2808470"},{"key":"ref99","first-page":"1599","article-title":"Formal security analysis of neural networks using symbolic intervals","author":"wang","year":"2018","journal-title":"27th USENIX Security Symposium ( USENIX Security 18)"},{"key":"ref96","article-title":"Prima: Precise and general neural network certification via multineuron convex relaxations","author":"m\u00fcller","year":"2021"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303750"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053011528"},{"key":"ref11","article-title":"Adversarial policies: Attacking deep reinforcement learning","author":"gleave","year":"2020"},{"key":"ref12","article-title":"Adversarial reinforcement learning","author":"uther","year":"1997","journal-title":"Proceedings of the AAAI Fall Symposium on Model Directed Autonomous Systems"},{"key":"ref13","article-title":"Robustness analysis of neural networks via efficient partitioning with applications in control systems","author":"everett","year":"2020","journal-title":"Systems & Control Letters"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3056046"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561348"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3133370"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3358228"},{"key":"ref17","article-title":"Pattern-recognizing control systems","author":"widrow","year":"1964","journal-title":"Compurter and Information Sciences"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3302504.3311807"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1109\/TAC.1970.1099405","article-title":"Learning control systems–review and outlook","volume":"15","author":"fu","year":"1970","journal-title":"IEEE Transactions on Automatic Control"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3302504.3311806"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/37.1868"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59152-6_30"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3069388"},{"key":"ref89","article-title":"Crown-ibp: Towards stable and efficient training of verifiably robust neural networks","author":"zhang","year":"2020"},{"key":"ref85","article-title":"Reachable set estimation for neural network control systems: A simulation-guided approach","author":"xiang","year":"2020","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304296"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3387168.3387244"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561956"}],"event":{"name":"2021 60th IEEE Conference on Decision and Control (CDC)","location":"Austin, TX, USA","start":{"date-parts":[[2021,12,14]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 60th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9682670\/9682776\/09683154.pdf?arnumber=9683154","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T19:06:14Z","timestamp":1726599974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9683154\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,14]]},"references-count":106,"URL":"https:\/\/doi.org\/10.1109\/cdc45484.2021.9683154","relation":{},"subject":[],"published":{"date-parts":[[2021,12,14]]}}}