Constructing Optimal Noise Channels for Enhanced Robustness in Quantum Machine Learning

arXiv:2404.16417v1 Announce Type: cross
Abstract: With the rapid advancement of Quantum Machine Learning (QML), the critical need to enhance security measures against adversarial attacks and protect QML models becomes increasingly evident. In this work, we outline the connection between quantum noise channels and differential privacy (DP), by constructing a family of noise channels which are inherently $\epsilon$-DP: $(\alpha, \gamma)$-channels. Through this approach, we successfully replicate the $\epsilon$-DP bounds observed for depolarizing and random rotation channels, thereby affirming the broad generality …

abstract advancement adversarial adversarial attacks arxiv attacks channels cs.ai cs.lg differential differential privacy machine machine learning noise privacy protect qml quant-ph quantum robustness security type work