Constructing Optimal Noise Channels for Enhanced Robustness in Quantum Machine Learning
CoRR(2024)
摘要
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 ϵ-DP: (α,
γ)-channels. Through this approach, we successfully replicate the
ϵ-DP bounds observed for depolarizing and random rotation channels,
thereby affirming the broad generality of our framework. Additionally, we use a
semi-definite program to construct an optimally robust channel. In a
small-scale experimental evaluation, we demonstrate the benefits of using our
optimal noise channel over depolarizing noise, particularly in enhancing
adversarial accuracy. Moreover, we assess how the variables α and
γ affect the certifiable robustness and investigate how different
encoding methods impact the classifier's robustness.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要