Investigating adversarial robustness via booster signal

Abstract

Deep Neural Networks (DNNs) have shown great performance in various applications such as autonomous driving systems, medical diagnosis, security systems, etc. However, recent works have demonstrated that deep neural networks are highly vulnerable to adversarial attacks. By manipulating the data imperceptibly, it changes the DNNs predictions. Since the existence of adversarial attacks can hurt the reliability of DNNs, it should be released. To defend against adversarial attacks, many defense strategies have been proposed, among which adversarial training has been demonstrated to be the most effective strategy. However, it has been known that adversarial training sometimes hurts natural accuracy. Then, many works focus on optimizing model parameters to handle the problem. Different from the previous approaches, in this research, we propose a new approach to improve the adversarial robustness by using an external signal rather than model parameters. In the proposed method, a well-optimized universal external signal called a booster signal is injected to the outside of the image which does not overlap with the original content. Then, it boosts both adversarial robustness and natural accuracy. The booster signal is optimized in parallel to model parameters step by step collaboratively. Experimental results show that the booster signal can improve both the natural and robust accuracies over the recent state-of-the-art adversarial training methods. Also, optimizing the booster signal is general and flexible enough to be adopted on any existing adversarial training methods.