 On the Tightness of Semidefinite Relaxations for Certifying Robustness
to Adversarial ExamplesNeural Information Processing Systems (NeurIPS), 2020 |
 Reach-SDP: Reachability Analysis of Closed-Loop Systems with Neural
Network Controllers via Semidefinite ProgrammingIEEE Conference on Decision and Control (CDC), 2020 |
 Tightened Convex Relaxations for Neural Network Robustness CertificationIEEE Conference on Decision and Control (CDC), 2020 |
 Overfitting in adversarially robust deep learningInternational Conference on Machine Learning (ICML), 2020 |
 Robust Model Predictive Shielding for Safe Reinforcement Learning with
Stochastic DynamicsIEEE International Conference on Robotics and Automation (ICRA), 2019 |
 Algorithms for Verifying Deep Neural Networks Changliu Liu Tomer Arnon Christopher Lazarus Christopher A. Strong Clark W. Barrett Mykel J. Kochenderfer |
