Reluplex: An efficient SMT solver for verifying deep neural networks G Katz, C Barrett, DL Dill, K Julian, MJ Kochenderfer International conference on computer aided verification, 97-117, 2017 | 1405 | 2017 |

The marabou framework for verification and analysis of deep neural networks G Katz, DA Huang, D Ibeling, K Julian, C Lazarus, R Lim, P Shah, ... International Conference on Computer Aided Verification, 443-452, 2019 | 287 | 2019 |

Deepsafe: A data-driven approach for assessing robustness of neural networks D Gopinath, G Katz, CS Păsăreanu, C Barrett International symposium on automated technology for verification and …, 2018 | 146 | 2018 |

Provably minimally-distorted adversarial examples N Carlini, G Katz, C Barrett, DL Dill arXiv preprint arXiv:1709.10207, 2017 | 139 | 2017 |

Towards proving the adversarial robustness of deep neural networks G Katz, C Barrett, DL Dill, K Julian, MJ Kochenderfer arXiv preprint arXiv:1709.02802, 2017 | 113 | 2017 |

SMTCoq: A plug-in for integrating SMT solvers into Coq B Ekici, A Mebsout, C Tinelli, C Keller, G Katz, A Reynolds, C Barrett International Conference on Computer Aided Verification, 126-133, 2017 | 73 | 2017 |

An abstraction-based framework for neural network verification YY Elboher, J Gottschlich, G Katz International Conference on Computer Aided Verification, 43-65, 2020 | 63 | 2020 |

Verifying deep-RL-driven systems Y Kazak, C Barrett, G Katz, M Schapira Proceedings of the 2019 workshop on network meets AI & ML, 83-89, 2019 | 51 | 2019 |

ScenarioTools–A tool suite for the scenario-based modeling and analysis of reactive systems J Greenyer, D Gritzner, T Gutjahr, F König, N Glade, A Marron, G Katz Science of Computer Programming 149, 15-27, 2017 | 36 | 2017 |

Toward scalable verification for safety-critical deep networks L Kuper, G Katz, J Gottschlich, K Julian, C Barrett, M Kochenderfer arXiv preprint arXiv:1801.05950, 2018 | 35 | 2018 |

On composing and proving the correctness of reactive behavior D Harel, A Kantor, G Katz, A Marron, L Mizrahi, G Weiss 2013 Proceedings of the International Conference on Embedded Software …, 2013 | 35 | 2013 |

Minimal Modifications of Deep Neural Networks using Verification. B Goldberger, G Katz, Y Adi, J Keshet LPAR 2020, 23rd, 2020 | 32 | 2020 |

Parallelization techniques for verifying neural networks H Wu, A Ozdemir, A Zeljic, K Julian, A Irfan, D Gopinath, S Fouladi, G Katz, ... # PLACEHOLDER_PARENT_METADATA_VALUE# 1, 128-137, 2020 | 32 | 2020 |

An SMT-based approach for verifying binarized neural networks G Amir, H Wu, C Barrett, G Katz International Conference on Tools and Algorithms for the Construction and …, 2021 | 31 | 2021 |

Non-intrusive repair of reactive programs D Harel, G Katz, A Marron, G Weiss 2012 IEEE 17th International Conference on Engineering of Complex Computer …, 2012 | 31 | 2012 |

Scenario-Based Modeling and Synthesis for Reactive Systems with Dynamic System Structure in ScenarioTools. J Greenyer, D Gritzner, G Katz, A Marron D&P@ MoDELS, 16-23, 2016 | 29 | 2016 |

Verifying recurrent neural networks using invariant inference Y Jacoby, C Barrett, G Katz International Symposium on Automated Technology for Verification and …, 2020 | 27 | 2020 |

Lazy proofs for DPLL (T)-based SMT solvers G Katz, C Barrett, C Tinelli, A Reynolds, L Hadarean 2016 Formal Methods in Computer-Aided Design (FMCAD), 93-100, 2016 | 27 | 2016 |

Simplifying neural networks using formal verification S Gokulanathan, A Feldsher, A Malca, C Barrett, G Katz NASA Formal Methods Symposium, 85-93, 2020 | 26* | 2020 |

Ground-Truth Adversarial Examples N Carlini, G Katz, C Barrett, DL Dill arXiv preprint arXiv:1709.10207v1, 2017 | 24 | 2017 |