DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples

Understand

Recent studies have shown that deep neural networks (DNN) are vulnerable to adversarial samples: maliciously-perturbed samples crafted to yield incorrect model outputs.

• Such attacks can severely undermine DNN systems, particularly in security-sensitive settings.
• It was observed that an adversary could easily generate adversarial samples by making a small perturbation on irrelevant feature dimensions that are unnecessary for the current classification task.
• To overcome this problem, we introduce a defensive mechanism called DeepCloak.