no code implementations • 29 Nov 2023 • Xiaoliang Liu, Furao Shen, Jian Zhao, Changhai Nie
RADAP employs innovative techniques, such as FCutout and F-patch, which use Fourier space sampling masks to improve the occlusion robustness of the FR model and the performance of the patch segmenter.
no code implementations • 29 Nov 2023 • Xiaoliang Liu, Furao Shen, Feng Han, Jian Zhao, Changhai Nie
Face recognition (FR) technology plays a crucial role in various applications, but its vulnerability to adversarial attacks poses significant security concerns.
no code implementations • 21 Jul 2022 • Xiaoliang Liu, Furao Shen, Jian Zhao, Changhai Nie
In this paper, we propose a new data processing and training method, called AugRmixAT, which can simultaneously improve the generalization ability and multiple robustness of neural network models.
no code implementations • 25 Jun 2022 • Xiaoliang Liu, Furao Shen, Jian Zhao, Changhai Nie
Furthermore, we propose a random meta-optimization strategy for ensembling several pre-trained face models to generate more general adversarial masks.
no code implementations • 18 May 2022 • Xiaoliang Liu, Furao Shen, Jian Zhao, Changhai Nie
Data augmentation plays a crucial role in enhancing the robustness and performance of machine learning models across various domains.