Paper Publications

Affiliation of Author(s):[1] Laboratory Of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, Chengdu, 611731, China; [2] School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China; [3] School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, 430070, China

Journal:arXiv

Key Words:Convolutional neural networks - Machine learning

Abstract:Hybrid Quantum Neural Networks (HQNNs) represent a promising advancement in Quantum Machine Learning (QML), yet their security has been rarely explored. In this paper, we present the first systematic study of backdoor attacks on HQNNs. We begin by proposing an attack framework and providing a theoretical analysis of the generalization bounds and minimum perturbation requirements for backdoor attacks on HQNNs. Next, we employ two classic backdoor attack methods on HQNNs and Convolutional Neural Networks (CNNs) to further investigate the robustness of HQNNs. Our experimental results demonstrate that HQNNs are more robust than CNNs, requiring more significant image modifications for successful attacks. Additionally, we introduce the Qcolor backdoor, which utilizes color shifts as triggers and employs the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to optimize hyperparameters. Through extensive experiments, we demonstrate the effectiveness, stealthiness, and robustness of the Qcolor backdoor. Copyright ? 2024, The Authors. All rights reserved.

Document Type:Preprint (PP)

Translation or Not:no