QuSecNets: Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attacks

Authors: Faiq Khalid, Hassan Ali, Hammad Tariq, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, Muhammad Shafique
Published: 2018-11-04 | Updated: 2020-05-14

Source: https://arxiv.org/abs/1811.01437

PDF: https://arxiv.org/pdf/1811.01437

AIにより推定されたラベル

モデルの頑健性保証 量子化手法 防御手法

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

Adversarial examples have emerged as a significant threat to machine learning algorithms, especially to the convolutional neural networks (CNNs). In this paper, we propose two quantization-based defense mechanisms, Constant Quantization (CQ) and Trainable Quantization (TQ), to increase the robustness of CNNs against adversarial examples. CQ quantizes input pixel intensities based on a “fixed” number of quantization levels, while in TQ, the quantization levels are “iteratively learned during the training phase”, thereby providing a stronger defense mechanism. We apply the proposed techniques on undefended CNNs against different state-of-the-art adversarial attacks from the open-source Cleverhans library. The experimental results demonstrate 50 10 generated from the MNIST and the CIFAR-10 datasets, respectively, on commonly used CNN (Conv2D(64, 8×8) – Conv2D(128, 6×6) – Conv2D(128, 5×5) – Dense(10) – Softmax()) available in Cleverhans library.