A Watermarking-Based Framework for Protecting Deep Image Classifiers Against Adversarial Attacks

Abstract

Although deep learning-based models have achieved tremendous success in imagerelated tasks, they are known to be vulnerable to adversarial examples-inputs with imperceptible, but subtly crafted perturbation which fool the models to produce incorrect outputs. To distinguish adversarial examples from benign images, in this thesis, we propose a novel watermarking-based framework for protecting deep image classifiers against adversarial attacks. The proposed framework consists of a watermark encoder, a possible adversary, and a detector followed by a deep image classifier to be protected.