Adversarial Robustness via Runtime Masking and Cleansing

no code implementations • ICML 2020 • Yi-Hsuan Wu, Chia-Hung Yuan, Shan-Hung (Brandon) Wu

Deep neural networks are shown to be vulnerable to adversarial attacks.

Adversarial Robustness

On the Trade-off between Adversarial and Backdoor Robustness

1 code implementation • NeurIPS 2020 • Cheng-Hsin Weng, Yan-Ting Lee, Shan-Hung (Brandon) Wu

Deep neural networks are shown to be susceptible to both adversarial attacks and backdoor attacks.

Adversarial Robustness

CNN^{2}: Viewpoint Generalization via a Binocular Vision

1 code implementation • NeurIPS 2019 • Wei-Da Chen, Shan-Hung (Brandon) Wu

Although recent efforts, such as the Capsule Networks, have been made to address this issue, these new models are either hard to train and/or incompatible with existing CNN-based techniques specialized for different applications.