Deep neural networks are widely used for nonlinear function approximation, with
applications ranging from computer vision to control. Although these networks involve the …

We show how to turn any classifier that classifies well under Gaussian noise into a new
classifier that is certifiably robust to adversarial perturbations under the L2 norm. While this" …

Deep reinforcement learning (DRL) has proven capable of superhuman performance on
many complex tasks. To achieve this success, DRL algorithms train a decision-making agent …

Adversarial examples that fool machine learning models, particularly deep neural networks,
have been a topic of intense research interest, with attacks and defenses being developed …

Recent works have shown the effectiveness of randomized smoothing as a scalable
technique for building neural network-based classifiers that are provably robust to $\ell_2 …

Bound propagation methods, when combined with branch and bound, are among the most
effective methods to formally verify properties of deep neural networks such as correctness …

Bound propagation based incomplete neural network verifiers such as CROWN are very
efficient and can significantly accelerate branch-and-bound (BaB) based complete …

Deep learning (DL) systems are increasingly deployed in safety-and security-critical
domains including self-driving cars and malware detection, where the correctness and …

AI-based systems are software systems with functionalities enabled by at least one AI
component (eg, for image-, speech-recognition, and autonomous driving). AI-based systems …

Designing neural networks with bounded Lipschitz constant is a promising way to obtain
certifiably robust classifiers against adversarial examples. However, the relevant progress …