{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T12:36:27Z","timestamp":1769949387020,"version":"3.49.0"},"reference-count":73,"publisher":"Association for Computing Machinery (ACM)","issue":"5s","license":[{"start":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T00:00:00Z","timestamp":1632268800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ONR","award":["N00014-20-1-2115"],"award-info":[{"award-number":["N00014-20-1-2115"]}]},{"name":"DARPA Assured Autonomy","award":["FA8750-18-C-0090"],"award-info":[{"award-number":["FA8750-18-C-0090"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2021,10,31]]},"abstract":"<jats:p>Recent advances in deep learning have enabled data-driven controller design for autonomous systems. However, verifying safety of such controllers, which are often hard-to-analyze neural networks, remains a challenge. Inspired by compositional strategies for program verification, we propose a framework for compositional learning and verification of neural network controllers. Our approach is to decompose the task (e.g., car navigation) into a sequence of subtasks (e.g., segments of the track), each corresponding to a different mode of the system (e.g., go straight or turn). Then, we learn a separate controller for each mode, and verify correctness by proving that (i) each controller is correct within its mode, and (ii) transitions between modes are correct. This compositional strategy not only improves scalability of both learning and verification, but also enables our approach to verify correctness for arbitrary compositions of the subtasks. To handle partial observability (e.g., LiDAR), we additionally learn and verify a mode predictor that predicts which controller to use. Finally, our framework also incorporates an algorithm that, given a set of controllers, automatically synthesizes the pre- and postconditions required by our verification procedure. We validate our approach in a case study on a simulation model of the F1\/10 autonomous car, a system that poses challenges for existing verification tools due to both its reliance on LiDAR observations, as well as the need to prove safety for complex track geometries. We leverage our framework to learn and verify a controller that safely completes any track consisting of an arbitrary sequence of five kinds of track segments.<\/jats:p>","DOI":"10.1145\/3477023","type":"journal-article","created":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T20:48:40Z","timestamp":1632343720000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":25,"title":["Compositional Learning and Verification of Neural Network Controllers"],"prefix":"10.1145","volume":"20","author":[{"given":"Radoslav","family":"Ivanov","sequence":"first","affiliation":[{"name":"University of Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kishor","family":"Jothimurugan","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steve","family":"Hsu","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaan","family":"Vaidya","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajeev","family":"Alur","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Osbert","family":"Bastani","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,9,22]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"[n.d.]. F1\/10 Autonomous Racing Competition. http:\/\/f1tenth.org.  [n.d.]. F1\/10 Autonomous Racing Competition. http:\/\/f1tenth.org."},{"key":"e_1_2_1_2_1","volume-title":"Conference on Decision and Control. IEEE, 1424\u20131431","author":"Akametalu Anayo K.","unstructured":"Anayo K. Akametalu , Jaime F. Fisac , Jeremy H. Gillula , Shahab Kaynama , Melanie N. Zeilinger , and Claire J. Tomlin . 2014. Reachability-based safe learning with Gaussian processes . In Conference on Decision and Control. IEEE, 1424\u20131431 . Anayo K. Akametalu, Jaime F. Fisac, Jeremy H. Gillula, Shahab Kaynama, Melanie N. Zeilinger, and Claire J. Tomlin. 2014. Reachability-based safe learning with Gaussian processes. In Conference on Decision and Control. IEEE, 1424\u20131431."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133904"},{"key":"e_1_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Mohammed Alshiekh Roderick Bloem R\u00fcdiger Ehlers Bettina K\u00f6nighofer Scott Niekum and Ufuk Topcu. 2018. Safe reinforcement learning via shielding. In AAAI.  Mohammed Alshiekh Roderick Bloem R\u00fcdiger Ehlers Bettina K\u00f6nighofer Scott Niekum and Ufuk Topcu. 2018. Safe reinforcement learning via shielding. In AAAI.","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2038642.2038685"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/0304-3975(94)00202-T"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/646874.709849"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/646732.703860"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314614"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157391"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327144.3327175"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360544"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294858"},{"key":"e_1_2_1_15_1","unstructured":"Zhangjie Cao Erdem B\u0131y\u0131k Woodrow Z. Wang Allan Raventos Adrien Gaidon Guy Rosman and Dorsa Sadigh. 2020. Reinforcement learning based control of imitative policies for near-accident driving. In Robotics: Science and Systems.  Zhangjie Cao Erdem B\u0131y\u0131k Woodrow Z. Wang Allan Raventos Adrien Gaidon Guy Rosman and Dorsa Sadigh. 2020. Reinforcement learning based control of imitative policies for near-accident driving. In Robotics: Science and Systems."},{"key":"e_1_2_1_16_1","volume-title":"International Conference on Computer Aided Verification. Springer, 258\u2013263","author":"Chen X.","unstructured":"X. Chen , E. \u00c1brah\u00e1m , and S. Sankaranarayanan . 2013. Flow*: An analyzer for non-linear hybrid systems . In International Conference on Computer Aided Verification. Springer, 258\u2013263 . X. Chen, E. \u00c1brah\u00e1m, and S. Sankaranarayanan. 2013. Flow*: An analyzer for non-linear hybrid systems. In International Conference on Computer Aided Verification. Springer, 258\u2013263."},{"key":"e_1_2_1_17_1","volume-title":"Efficient bipedal robots based on passive-dynamic walkers. Science 307, 5712","author":"Collins Steve","year":"2005","unstructured":"Steve Collins , Andy Ruina , Russ Tedrake , and Martijn Wisse . 2005. Efficient bipedal robots based on passive-dynamic walkers. Science 307, 5712 ( 2005 ), 1082\u20131085. Steve Collins, Andy Ruina, Russ Tedrake, and Martijn Wisse. 2005. Efficient bipedal robots based on passive-dynamic walkers. Science 307, 5712 (2005), 1082\u20131085."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2002.804474"},{"key":"e_1_2_1_19_1","volume-title":"Seshia","author":"Dreossi Tommaso","year":"2019","unstructured":"Tommaso Dreossi , Daniel J. Fremont , Shromona Ghosh , Edward Kim , Hadi Ravanbakhsh , Marcell Vazquez-Chanlatte , and Sanjit A . Seshia . 2019 . Verifai : A toolkit for the formal design and analysis of artificial intelligence-based systems. In CAV. Springer , 432\u2013442. Tommaso Dreossi, Daniel J. Fremont, Shromona Ghosh, Edward Kim, Hadi Ravanbakhsh, Marcell Vazquez-Chanlatte, and Sanjit A. Seshia. 2019. Verifai: A toolkit for the formal design and analysis of artificial intelligence-based systems. In CAV. Springer, 432\u2013442."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2019.0317"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302504.3311807"},{"key":"e_1_2_1_22_1","volume-title":"NASA Formal Methods Symposium. Springer, 121\u2013138","author":"Dutta S.","unstructured":"S. Dutta , S. Jha , S. Sankaranarayanan , and A. Tiwari . 2018. Output range analysis for deep feedforward neural networks . In NASA Formal Methods Symposium. Springer, 121\u2013138 . S. Dutta, S. Jha, S. Sankaranarayanan, and A. Tiwari. 2018. Output range analysis for deep feedforward neural networks. In NASA Formal Methods Symposium. Springer, 121\u2013138."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68167-2_19"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scico.2007.01.015"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455312"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/647540.730008"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314633"},{"key":"e_1_2_1_28_1","volume-title":"Addressing function approximation error in actor-critic methods. arXiv preprint arXiv:1802.09477","author":"Fujimoto Scott","year":"2018","unstructured":"Scott Fujimoto , Herke van Hoof , and David Meger . 2018. Addressing function approximation error in actor-critic methods. arXiv preprint arXiv:1802.09477 ( 2018 ). Scott Fujimoto, Herke van Hoof, and David Meger. 2018. Addressing function approximation error in actor-critic methods. arXiv preprint arXiv:1802.09477 (2018)."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3106237.3106277"},{"key":"e_1_2_1_30_1","volume-title":"Hierarchical Program-Triggered Reinforcement Learning Agents For Automated Driving. arXiv preprint arXiv:2103.13861","author":"Gangopadhyay Briti","year":"2021","unstructured":"Briti Gangopadhyay , Harshit Soora , and Pallab Dasgupta . 2021. Hierarchical Program-Triggered Reinforcement Learning Agents For Automated Driving. arXiv preprint arXiv:2103.13861 ( 2021 ). Briti Gangopadhyay, Harshit Soora, and Pallab Dasgupta. 2021. Hierarchical Program-Triggered Reinforcement Learning Agents For Automated Driving. arXiv preprint arXiv:2103.13861 (2021)."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08867-9_5"},{"key":"e_1_2_1_32_1","volume-title":"IEEE Symposium on Security and Privacy.","author":"Gehr T.","unstructured":"T. Gehr , M. Mirman , D. Drachsler-Cohen , P. Tsankov , S. Chaudhuri , and M. Vechev . 2018. AI2: Safety and robustness certification of neural networks with abstract interpretation . In IEEE Symposium on Security and Privacy. T. Gehr, M. Mirman, D. Drachsler-Cohen, P. Tsankov, S. Chaudhuri, and M. Vechev. 2018. AI2: Safety and robustness certification of neural networks with abstract interpretation. In IEEE Symposium on Security and Privacy."},{"key":"e_1_2_1_33_1","volume-title":"Explaining and Harnessing Adversarial Examples. In International Conference on Learning Representations.","author":"Goodfellow Ian","year":"2015","unstructured":"Ian Goodfellow , Jonathon Shlens , and Christian Szegedy . 2015 . Explaining and Harnessing Adversarial Examples. In International Conference on Learning Representations. Ian Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and Harnessing Adversarial Examples. In International Conference on Learning Representations."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/363235.363259"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3358228"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63387-9_1"},{"key":"e_1_2_1_37_1","volume-title":"International Conference on Learning Representations.","author":"Inala Jeevana Priya","year":"2020","unstructured":"Jeevana Priya Inala , Osbert Bastani , Zenna Tavares , and Armando Solar-Lezama . 2020 . Synthesizing Programmatic Policies that Inductively Generalize . In International Conference on Learning Representations. Jeevana Priya Inala, Osbert Bastani, Zenna Tavares, and Armando Solar-Lezama. 2020. Synthesizing Programmatic Policies that Inductively Generalize. In International Conference on Learning Representations."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3365365.3382216"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302504.3311806"},{"key":"e_1_2_1_40_1","volume-title":"Generative Modeling of Environments with Scene Grammars and Variational Inference. In 2020 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 6891\u20136897","author":"Izatt Gregory","year":"2020","unstructured":"Gregory Izatt and Russ Tedrake . 2020 . Generative Modeling of Environments with Scene Grammars and Variational Inference. In 2020 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 6891\u20136897 . Gregory Izatt and Russ Tedrake. 2020. Generative Modeling of Environments with Scene Grammars and Variational Inference. In 2020 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 6891\u20136897."},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455455"},{"key":"e_1_2_1_42_1","volume-title":"Reluplex: An efficient SMT solver for verifying deep neural networks. In International Conference on Computer Aided Verification","author":"Katz G.","year":"2017","unstructured":"G. Katz , C. Barrett , D. L. Dill , K. Julian , and M. J. Kochenderfer . 2017 . Reluplex: An efficient SMT solver for verifying deep neural networks. In International Conference on Computer Aided Verification . Springer , 97\u2013117. G. Katz, C. Barrett, D. L. Dill, K. Julian, and M. J. Kochenderfer. 2017. Reluplex: An efficient SMT solver for verifying deep neural networks. In International Conference on Computer Aided Verification. Springer, 97\u2013117."},{"key":"e_1_2_1_43_1","volume-title":"Conference on Robot Learning.","author":"Khan Arbaaz","year":"2020","unstructured":"Arbaaz Khan , Ekaterina Tolstaya , Alejandro Ribeiro , and Vijay Kumar . 2020 . Graph policy gradients for large scale robot control . In Conference on Robot Learning. Arbaaz Khan, Ekaterina Tolstaya, Alejandro Ribeiro, and Vijay Kumar. 2020. Graph policy gradients for large scale robot control. In Conference on Robot Learning."},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-46681-0_15"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157509"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946684"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196867"},{"key":"e_1_2_1_48_1","unstructured":"T. P. Lillicrap J. J. Hunt A. Pritzel N. Heess T. Erez Y. Tassa D. Silver and D. Wierstra. 2015. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015).  T. P. Lillicrap J. J. Hunt A. Pritzel N. Heess T. Erez Y. Tassa D. Silver and D. Wierstra. 2015. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)."},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.5555\/239587.239653"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.5555\/3042573.3042759"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327144.3327250"},{"key":"e_1_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Nikhil Naik and Pierluigi Nuzzo. 2020. Robustness Contracts for Scalable Verification of Neural Network-Enabled Cyber-Physical Systems. In 2020 18th ACM-IEEE International Conference on Formal Methods and Models for System Design (MEMOCODE). IEEE 1\u201312.  Nikhil Naik and Pierluigi Nuzzo. 2020. Robustness Contracts for Scalable Verification of Neural Network-Enabled Cyber-Physical Systems. In 2020 18th ACM-IEEE International Conference on Formal Methods and Models for System Design (MEMOCODE). IEEE 1\u201312.","DOI":"10.1109\/MEMOCODE51338.2020.9315118"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.5555\/646874.759754"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327546.3327650"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980983.2908099"},{"key":"e_1_2_1_56_1","volume-title":"Safe, Autonomous and Intelligent Vehicles","author":"P\u0103s\u0103reanu Corina S.","unstructured":"Corina S. P\u0103s\u0103reanu , Divya Gopinath , and Huafeng Yu. 2019. Compositional verification for autonomous systems with deep learning components . In Safe, Autonomous and Intelligent Vehicles . Springer , 187\u2013197. Corina S. P\u0103s\u0103reanu, Divya Gopinath, and Huafeng Yu. 2019. Compositional verification for autonomous systems with deep learning components. In Safe, Autonomous and Intelligent Vehicles. Springer, 187\u2013197."},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24743-2_32"},{"key":"e_1_2_1_58_1","volume-title":"Vehicle dynamics and control","author":"Rajamani Rajesh","unstructured":"Rajesh Rajamani . 2011. Vehicle dynamics and control . Springer Science & Business Media . Rajesh Rajamani. 2011. Vehicle dynamics and control. Springer Science & Business Media."},{"key":"e_1_2_1_59_1","volume-title":"Proc. of NIPS Workshop Learn. Inference Control Multi-Agent Syst","author":"Shalev-Shwartz Shai","year":"2016","unstructured":"Shai Shalev-Shwartz , Shaked Shammah , and Amnon Shashua . 2016 . Safe, multi-agent, reinforcement learning for autonomous driving . Proc. of NIPS Workshop Learn. Inference Control Multi-Agent Syst (2016). Shai Shalev-Shwartz, Shaked Shammah, and Amnon Shashua. 2016. Safe, multi-agent, reinforcement learning for autonomous driving. Proc. of NIPS Workshop Learn. Inference Control Multi-Agent Syst (2016)."},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10703-016-0248-5"},{"key":"e_1_2_1_61_1","volume-title":"Nori","author":"Sharma Rahul","year":"2013","unstructured":"Rahul Sharma , Saurabh Gupta , Bharath Hariharan , Alex Aiken , and Aditya V . Nori . 2013 . Verification as learning geometric concepts. In International Static Analysis Symposium. Springer , 388\u2013411. Rahul Sharma, Saurabh Gupta, Bharath Hariharan, Alex Aiken, and Aditya V. Nori. 2013. Verification as learning geometric concepts. In International Static Analysis Symposium. Springer, 388\u2013411."},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.5555\/1714168"},{"key":"e_1_2_1_63_1","volume-title":"Conference on Robot Learning","author":"Sun Dawei","year":"2020","unstructured":"Dawei Sun , Susmit Jha , and Chuchu Fan . 2020 . Learning certified control using contraction metric . Conference on Robot Learning (2020). Dawei Sun, Susmit Jha, and Chuchu Fan. 2020. Learning certified control using contraction metric. Conference on Robot Learning (2020)."},{"key":"e_1_2_1_64_1","volume-title":"International Conference on Learning Representations.","author":"Sun Shao-Hua","unstructured":"Shao-Hua Sun , Te-Lin Wu , and Joseph J. Lim . 2019. Program guided agent . In International Conference on Learning Representations. Shao-Hua Sun, Te-Lin Wu, and Joseph J. Lim. 2019. Program guided agent. In International Conference on Learning Representations."},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302504.3311802"},{"key":"e_1_2_1_66_1","volume-title":"International Conference on Learning Representations.","author":"Szegedy Christian","year":"2014","unstructured":"Christian Szegedy , Wojciech Zaremba , Ilya Sutskever , Joan Bruna , Dumitru Erhan , Ian Goodfellow , and Rob Fergus . 2014 . Intriguing properties of neural networks . In International Conference on Learning Representations. Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. 2014. Intriguing properties of neural networks. In International Conference on Learning Representations."},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910369189"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3358230"},{"key":"e_1_2_1_69_1","volume-title":"International Conference on Machine Learning. PMLR, 5045\u20135054","author":"Verma Abhinav","year":"2018","unstructured":"Abhinav Verma , Vijayaraghavan Murali , Rishabh Singh , Pushmeet Kohli , and Swarat Chaudhuri . 2018 . Programmatically interpretable reinforcement learning . In International Conference on Machine Learning. PMLR, 5045\u20135054 . Abhinav Verma, Vijayaraghavan Murali, Rishabh Singh, Pushmeet Kohli, and Swarat Chaudhuri. 2018. Programmatically interpretable reinforcement learning. In International Conference on Machine Learning. PMLR, 5045\u20135054."},{"key":"e_1_2_1_70_1","volume-title":"Conference on Decision and Control (CDC). IEEE, 7130\u20137135","author":"Kim","unstructured":"Kim P. Wabersich and Melanie N. Zeilinger. 2018. Linear model predictive safety certification for learning-based control . In Conference on Decision and Control (CDC). IEEE, 7130\u20137135 . Kim P. Wabersich and Melanie N. Zeilinger. 2018. Linear model predictive safety certification for learning-based control. In Conference on Decision and Control (CDC). IEEE, 7130\u20137135."},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327345.3327533"},{"key":"e_1_2_1_72_1","volume-title":"Towards Fast Computation of Certified Robustness for ReLU Networks. In International Conference on Machine Learning. 5273\u20135282","author":"Weng T.","unstructured":"T. Weng , H. Zhang , H. Chen , Z. Song , C. Hsieh , L. Daniel , D. Boning , and I. Dhillon . 2018 . Towards Fast Computation of Certified Robustness for ReLU Networks. In International Conference on Machine Learning. 5273\u20135282 . T. Weng, H. Zhang, H. Chen, Z. Song, C. Hsieh, L. Daniel, D. Boning, and I. Dhillon. 2018. Towards Fast Computation of Certified Robustness for ReLU Networks. In International Conference on Machine Learning. 5273\u20135282."},{"key":"e_1_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314638"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477023","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477023","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:46Z","timestamp":1750188646000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477023"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,22]]},"references-count":73,"journal-issue":{"issue":"5s","published-print":{"date-parts":[[2021,10,31]]}},"alternative-id":["10.1145\/3477023"],"URL":"https:\/\/doi.org\/10.1145\/3477023","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,22]]},"assertion":[{"value":"2021-04-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}