A Coverage-Guided Testing Framework for Quantum Neural Networks

Quantum Neural Networks (QNNs) combine quantum computing and neural networks, leveraging quantum properties such as superposition and entanglement to improve machine learning models. These quantum characteristics enable QNNs to potentially outperform classical neural networks in tasks such as quantum chemistry simulations, optimization problems, and quantum-enhanced machine learning. However, they also introduce significant challenges in verifying the correctness and reliability of QNNs. To address this, we propose QCov, a set of test coverage criteria specifically designed for QNNs to systematically evaluate QNN state exploration during testing, focusing on superposition and entanglement. These criteria help detect quantum-specific defects and anomalies. Quantum Neural Networks (QNNs) Cong et al. (2018) represent a significant advancement in computational technology, combining the principles of quantum mechanics with neural network mechanisms. By leveraging quantum properties such as superposition and entanglement, QNNs have the potential to solve complex problems more efficiently than classical neural networks, particularly in areas like image classification Li et al. (2022b); Shi et al. (2023); Henderson et al. (2019); Alam et al. (2021) and sequential data learning Bausch (2020); Yu et al. (2024). Despite this early success, similar to Deep Neural Networks (DNNs) LeCun et al. (1998a); He et al. (2015); Howard et al. (2017), QNNs have been shown to be vulnerable to adversarial Lu et al. (2019) and backdoor attacks Chu et al. (2023a;b), raising concerns about their security and robustness. A recent work, QuanTest Shi et al. (2024), introduced the first adversarial testing framework for QNNs, using an entanglement-guided optimization algorithm to generate adversarial inputs and capture erroneous behaviors. However, QuanTest focuses primarily on individual inputs, lacking a comprehensive evaluation of overall test adequacy for QNNs. Additionally, due to the complexity of the Hilbert space, which grows exponentially with the number of qubits, it is impractical to manually test QNNs thoroughly. This highlights the urgent need for a comprehensive testing framework to assess the test adequacy of QNNs. To ensure system quality, numerous testing techniques have been developed for deep learning (DL) systems Zhang et al. (2020); Wang et al. (2024) and traditional quantum software Wang et al. (2021a;b); Fortunato et al. (2022a); Xia et al. (2024) from various perspectives.