Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging

no code implementations • 22 Aug 2023 • Xiaojun Jia, Yuefeng Chen, Xiaofeng Mao, Ranjie Duan, Jindong Gu, Rong Zhang, Hui Xue, Xiaochun Cao

In this paper, we conduct a comprehensive study of over 10 fast adversarial training methods in terms of adversarial robustness and training costs.

Adversarial Robustness Data Augmentation

Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training

no code implementations • 24 Jul 2023 • Gege Qi, Yuefeng Chen, Xiaofeng Mao, Xiaojun Jia, Ranjie Duan, Rong Zhang, Hui Xue

Developing a practically-robust automatic speech recognition (ASR) is challenging since the model should not only maintain the original performance on clean samples, but also achieve consistent efficacy under small volume perturbations and large domain shifts.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Enhance the Visual Representation via Discrete Adversarial Training

1 code implementation • 16 Sep 2022 • Xiaofeng Mao, Yuefeng Chen, Ranjie Duan, Yao Zhu, Gege Qi, Shaokai Ye, Xiaodan Li, Rong Zhang, Hui Xue

For borrowing the advantage from NLP-style AT, we propose Discrete Adversarial Training (DAT).

Domain Generalization Image Classification +2

AdvDrop: Adversarial Attack to DNNs by Dropping Information

1 code implementation • ICCV 2021 • Ranjie Duan, Yuefeng Chen, Dantong Niu, Yun Yang, A. K. Qin, Yuan He

Human can easily recognize visual objects with lost information: even losing most details with only contour reserved, e. g. cartoon.

Adversarial Attack Adversarial Robustness

Towards Robust Vision Transformer

2 code implementations • CVPR 2022 • Xiaofeng Mao, Gege Qi, Yuefeng Chen, Xiaodan Li, Ranjie Duan, Shaokai Ye, Yuan He, Hui Xue

By using and combining robust components as building blocks of ViTs, we propose Robust Vision Transformer (RVT), which is a new vision transformer and has superior performance with strong robustness.

Domain Generalization Image Classification +1

Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink

1 code implementation • CVPR 2021 • Ranjie Duan, Xiaofeng Mao, A. K. Qin, Yun Yang, Yuefeng Chen, Shaokai Ye, Yuan He

Though it is well known that the performance of deep neural networks (DNNs) degrades under certain light conditions, there exists no study on the threats of light beams emitted from some physical source as adversarial attacker on DNNs in a real-world scenario.

Adversarial Attack

Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles

1 code implementation • CVPR 2020 • Ranjie Duan, Xingjun Ma, Yisen Wang, James Bailey, A. K. Qin, Yun Yang

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples.