research
∙
03/31/2023
POLAR-Express: Efficient and Precise Formal Reachability Analysis of Neural-Network Controlled Systems
Neural networks (NNs) playing the role of controllers have demonstrated ...
share
research
∙
06/25/2021
POLAR: A Polynomial Arithmetic Framework for Verifying Neural-Network Controlled Systems
We propose POLAR, a polynomial arithmetic framework that leverages polyn...
research
∙
02/26/2021
Robust Deep Reinforcement Learning via Multi-View Information Bottleneck
Deep reinforcement learning (DRL) agents are often sensitive to visual c...
research
∙
08/13/2020
Adversarial Training and Provable Robustness: A Tale of Two Objectives
We propose a principled framework that combines adversarial training and...
research
∙
06/25/2019
ReachNN: Reachability Analysis of Neural-Network Controlled Systems
Applying neural networks as controllers in dynamical systems has shown g...
research
∙
03/06/2019