J Ji, T Qiu, B Chen, B Zhang, H Lou, K Wang… - arXiv preprint arXiv …, 2023 - arxiv.org
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 …
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 …
A Mao, M Mohri, Y Zhong - International conference on …, 2023 - proceedings.mlr.press
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 …
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 …
X Jia, Y Zhang, B Wu, K Ma… - Proceedings of the …, 2022 - openaccess.thecvf.com
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 …
K Mahmood, R Mahmood… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
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 …
Z Jiang, T Chen, T Chen… - Advances in neural …, 2020 - proceedings.neurips.cc
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 …