Critical Evaluation of Quantum Machine Learning for Adversarial Robustness

Authors: Saeefa Rubaiyet Nowmi, Jesus Lopez, Md Mahmudul Alam Imon, Shahrooz Pouryouse, Mohammad Saidur Rahman
Published: 2025-11-19

Source: https://arxiv.org/abs/2511.14989

PDF: https://arxiv.org/pdf/2511.14989

AIにより推定されたラベル

バックドア攻撃 量子機械学習 敵対的学習

※ 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

Quantum Machine Learning (QML) integrates quantum computational principles into learning algorithms, offering improved representational capacity and computational efficiency. Nevertheless, the security and robustness of QML systems remain underexplored, especially under adversarial conditions. In this paper, we present a systematization of adversarial robustness in QML, integrating conceptual organization with empirical evaluation across three threat models-black-box, gray-box, and white-box. We implement representative attacks in each category, including label-flipping for black-box, QUID encoder-level data poisoning for gray-box, and FGSM and PGD for white-box, using Quantum Neural Networks (QNNs) trained on two datasets from distinct domains: MNIST from computer vision and AZ-Class from Android malware, across multiple circuit depths (2, 5, 10, and 50 layers) and two encoding schemes (angle and amplitude). Our evaluation shows that amplitude encoding yields the highest clean accuracy (93