Defend Deep Neural Networks Against Adversarial Examples via Fixed and Dynamic Quantized Activation Functions
This work addresses the problem of adversarial attacks for deep learning practitioners by introducing a novel defense approach, though it appears incremental as it builds on existing quantization techniques.
The paper tackles the vulnerability of deep neural networks to adversarial attacks by proposing a method that merges network compactness and robustness through quantization of activation functions, achieving improved robustness on MNIST and CIFAR-10 datasets under various white-box and black-box attacks.
Recent studies have shown that deep neural networks (DNNs) are vulnerable to adversarial attacks. To this end, many defense approaches that attempt to improve the robustness of DNNs have been proposed. In a separate and yet related area, recent works have explored to quantize neural network weights and activation functions into low bit-width to compress model size and reduce computational complexity. In this work, we find that these two different tracks, namely the pursuit of network compactness and robustness, can be merged into one and give rise to networks of both advantages. To the best of our knowledge, this is the first work that uses quantization of activation functions to defend against adversarial examples. We also propose to train robust neural networks by using adaptive quantization techniques for the activation functions. Our proposed Dynamic Quantized Activation (DQA) is verified through a wide range of experiments with the MNIST and CIFAR-10 datasets under different white-box attack methods, including FGSM, PGD, and C & W attacks. Furthermore, Zeroth Order Optimization and substitute model-based black-box attacks are also considered in this work. The experimental results clearly show that the robustness of DNNs could be greatly improved using the proposed DQA.