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

AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, the potential large-scale risks associated with misaligned AI …

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 …

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 …

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 …

Adversarial training (AT) is always formulated as a minimax problem, of which the
performance depends on the inner optimization that involves the generation of adversarial …

Recent advances in attention-based networks have shown that Vision Transformers can
achieve state-of-the-art or near state-of-the-art results on many image classification tasks …

Recent work has shown that, when integrated with adversarial training, self-supervised pre-
training can lead to state-of-the-art robustness In this work, we improve robustness-aware …

Data augmentation is a simple yet effective way to improve the robustness of deep neural
networks (DNNs). Diversity and hardness are two complementary dimensions of data …

Deep neural networks (DNNs) are known to be vulnerable to adversarial attacks. A range of
defense methods have been proposed to train adversarially robust DNNs, among which …