Machine learning is increasingly used to inform decision making in sensitive situations
where decisions have consequential effects on individuals' lives. In these settings, in …

Adversarial training is one of the most effective approaches defending against adversarial
examples for deep learning models. Unlike other defense strategies, adversarial training …

It has been recognized that the data generated by the denoising diffusion probabilistic
model (DDPM) improves adversarial training. After two years of rapid development in …

Cross-entropy is a widely used loss function in applications. It coincides with the logistic loss
applied to the outputs of a neural network, when the softmax is used. But, what guarantees …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

Large vision-language models (LVLMs) have shown remarkable abilities in understanding
visual information with human languages. However, LVLMs still suffer from object …

Recent work argues that robust training requires substantially larger datasets than those
required for standard classification. On CIFAR-10 and CIFAR-100, this translates into a …

Adversarial training suffers from robust overfitting, a phenomenon where the robust test
accuracy starts to decrease during training. In this paper, we focus on reducing robust …

For machine learning systems to be reliable, we must understand their performance in
unseen, out-of-distribution environments. In this paper, we empirically show that out-of …

Machine learning (ML) systems are rapidly increasing in size, are acquiring new
capabilities, and are increasingly deployed in high-stakes settings. As with other powerful …