Defending against Adversarial Attack towards Deep Neural Networks via Collaborative Multi-task Training

no code implementations • 14 Mar 2018 • Derek Wang, Chaoran Li, Sheng Wen, Surya Nepal, Yang Xiang

For example, proactive defending methods are invalid against grey-box or white-box attacks, while reactive defending methods are challenged by low-distortion adversarial examples or transferring adversarial examples.

Adversarial Attack