Evaluating Efficacy of Model Stealing Attacks and Defenses on Quantum Neural Networks

arXiv:2402.11687v1 Announce Type: cross
Abstract: Cloud hosting of quantum machine learning (QML) models exposes them to a range of vulnerabilities, the most significant of which is the model stealing attack. In this study, we assess the efficacy of such attacks in the realm of quantum computing. We conducted comprehensive experiments on various datasets with multiple QML model architectures. Our findings revealed that model stealing attacks can produce clone models achieving up to $0.9\times$ and $0.99\times$ clone test accuracy when trained …

abstract arxiv attacks cloud computing cs.cr cs.lg hosting machine machine learning networks neural networks qml quant-ph quantum quantum computing quantum neural networks stealing study them type vulnerabilities