Smarter applications are making better use of the insights gleaned from data, having an
impact on every industry and research discipline. At the core of this revolution lies the tools …

Deep neural networks (DNNs) are machine learning algorithms that have revolutionized
computer vision due to their remarkable successes in tasks like object classification and …

As a research community, we are still lacking a systematic understanding of the progress on
adversarial robustness which often makes it hard to identify the most promising ideas in …

Backdoor learning is an emerging and vital topic for studying deep neural networks'
vulnerability (DNNs). Many pioneering backdoor attack and defense methods are being …

Deep neural networks excel at finding hierarchical representations that solve complex tasks
over large datasets. How can we humans understand these learned representations? In this …

Adaptive attacks have (rightfully) become the de facto standard for evaluating defenses to
adversarial examples. We find, however, that typical adaptive evaluations are incomplete …

Fine-tuning pretrained language models (LMs) without making any architectural changes
has become a norm for learning various language downstream tasks. However, for non …

We identify and formalize a fundamental gradient descent phenomenon resulting in a
learning proclivity in over-parameterized neural networks. Gradient Starvation arises when …

We propose to reinterpret a standard discriminative classifier of p (y| x) as an energy based
model for the joint distribution p (x, y). In this setting, the standard class probabilities can be …

We identify a trade-off between robustness and accuracy that serves as a guiding principle
in the design of defenses against adversarial examples. Although this problem has been …