One obstacle to applying reinforcement learning algorithms to real-world problems is the
lack of suitable reward functions. Designing such reward functions is difficult in part because …

The open-world deployment of Machine Learning (ML) algorithms in safety-critical
applications such as autonomous vehicles needs to address a variety of ML vulnerabilities …

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" …

Large-scale pre-trained language models have achieved tremendous success across a
wide range of natural language understanding (NLU) tasks, even surpassing human …

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 …

We show that there may exist an inherent tension between the goal of adversarial
robustness and that of standard generalization. Specifically, training robust models may not …

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 …

Contrastive learning (CL) can learn generalizable feature representations and achieve state-
of-the-art performance of downstream tasks by finetuning a linear classifier on top of it …

Recent work has shown that it is possible to train deep neural networks that are provably
robust to norm-bounded adversarial perturbations. Most of these methods are based on …

Despite their impressive performance on diverse tasks, neural networks fail catastrophically
in the presence of adversarial inputs—imperceptibly but adversarially perturbed versions of …