Adv-4-Adv: Thwarting Changing Adversarial Perturbations via Adversarial Domain Adaptation

no code implementations • 1 Dec 2021 • Tianyue Zheng, Zhe Chen, Shuya Ding, Chao Cai, Jun Luo

Whereas adversarial training can be useful against specific adversarial perturbations, they have also proven ineffective in generalizing towards attacks deviating from those used for training.

Domain Adaptation

RF-Net: a Unified Meta-learning Framework for RF-enabled One-shot Human Activity Recognition

1 code implementation • 29 Oct 2021 • Shuya Ding, Zhe Chen, Tianyue Zheng, Jun Luo

Radio-Frequency (RF) based device-free Human Activity Recognition (HAR) rises as a promising solution for many applications.

Human Activity Recognition Meta-Learning

Enhancing RF Sensing with Deep Learning: A Layered Approach

no code implementations • 28 Oct 2021 • Tianyue Zheng, Zhe Chen, Shuya Ding, Jun Luo

To better understand this potential, this article takes a layered approach to summarize RF sensing enabled by deep learning.

Enhancing Intrinsic Adversarial Robustness via Feature Pyramid Decoder

1 code implementation • CVPR 2020 • Guanlin Li, Shuya Ding, Jun Luo, Chang Liu

Whereas adversarial training is employed as the main defence strategy against specific adversarial samples, it has limited generalization capability and incurs excessive time complexity.

Adversarial Robustness Decoder +3