Efficient Defenses Against Adversarial Attacks
This addresses a critical security threat for AI systems using DNNs, but it is incremental as it builds on existing defense approaches.
The paper tackles the problem of adversarial attacks on deep neural networks by proposing a new defense method that reinforces DNN structure to improve stability and reduce vulnerability, achieving better performance than state-of-the-art defenses with minimal training overhead and maintained clean sample accuracy.
Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention of undermining a system. In the case of DNNs, the lack of better understanding of their working has prevented the development of efficient defenses. In this paper, we propose a new defense method based on practical observations which is easy to integrate into models and performs better than state-of-the-art defenses. Our proposed solution is meant to reinforce the structure of a DNN, making its prediction more stable and less likely to be fooled by adversarial samples. We conduct an extensive experimental study proving the efficiency of our method against multiple attacks, comparing it to numerous defenses, both in white-box and black-box setups. Additionally, the implementation of our method brings almost no overhead to the training procedure, while maintaining the prediction performance of the original model on clean samples.