QuantumLeak: Stealing Quantum Neural Networks from Cloud-based NISQ Machines
This addresses security vulnerabilities for quantum computing users by enabling more effective model extraction, though it is incremental as it builds on classical methods.
The paper tackled the problem of stealing quantum neural networks from cloud-based NISQ machines, introducing QuantumLeak, which improved local VQC accuracy by 4.99% to 7.35% compared to existing techniques.
Variational quantum circuits (VQCs) have become a powerful tool for implementing Quantum Neural Networks (QNNs), addressing a wide range of complex problems. Well-trained VQCs serve as valuable intellectual assets hosted on cloud-based Noisy Intermediate Scale Quantum (NISQ) computers, making them susceptible to malicious VQC stealing attacks. However, traditional model extraction techniques designed for classical machine learning models encounter challenges when applied to NISQ computers due to significant noise in current devices. In this paper, we introduce QuantumLeak, an effective and accurate QNN model extraction technique from cloud-based NISQ machines. Compared to existing classical model stealing techniques, QuantumLeak improves local VQC accuracy by 4.99\%$\sim$7.35\% across diverse datasets and VQC architectures.