AdvQuNN: A Methodology for Analyzing the Adversarial Robustness of Quanvolutional Neural Networks (2403.05596v2)
Abstract: Recent advancements in quantum computing have led to the development of hybrid quantum neural networks (HQNNs) that employ a mixed set of quantum layers and classical layers, such as Quanvolutional Neural Networks (QuNNs). While several works have shown security threats of classical neural networks, such as adversarial attacks, their impact on QuNNs is still relatively unexplored. This work tackles this problem by designing AdvQuNN, a specialized methodology to investigate the robustness of HQNNs like QuNNs against adversarial attacks. It employs different types of Ansatzes as parametrized quantum circuits and different types of adversarial attacks. This study aims to rigorously assess the influence of quantum circuit architecture on the resilience of QuNN models, which opens up new pathways for enhancing the robustness of QuNNs and advancing the field of quantum cybersecurity. Our results show that, compared to classical convolutional networks, QuNNs achieve up to 60\% higher robustness for the MNIST and 40\% for FMNIST datasets.
- Laith Alzubaidi et al. 2021. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of big Data (2021).
- Li Deng. 2012. The mnist database of handwritten digit images for machine learning research. IEEE Signal Processing Magazine (2012).
- Yinpeng Dong et al. 2018. Boosting Adversarial Attacks With Momentum. In CVPR.
- Explaining and Harnessing Adversarial Examples. In ICLR.
- Ji Guan et al. 2021. Robustness verification of quantum classifiers. In CAV.
- Amira Guesmi et al. 2023. Physical Adversarial Attacks for Camera-Based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlook. IEEE Access (2023).
- Yanming Guo et al. 2018. A review of semantic segmentation using deep neural networks. International journal of multimedia information retrieval (2018).
- Maxwell Henderson et al. 2020. Quanvolutional neural networks: powering image recognition with quantum circuits. Quantum Machine Intelligence (2020).
- Shui-Yuan Huang et al. 2023. Image classification and adversarial robustness analysis based on hybrid quantum–classical convolutional neural network. Optics Communications (2023).
- Ryan LaRose and Brian Coyle. 2020. Robust data encodings for quantum classifiers. Physical Review A (2020).
- Zewen Li et al. 2021. A survey of convolutional neural networks: analysis, applications, and prospects. IEEE TNNLS (2021).
- Nana Liu and Peter Wittek. 2020. Vulnerability of quantum classification to adversarial perturbations. Physical Review A (2020).
- Sirui Lu et al. 2020. Quantum adversarial machine learning. Physical Review Research (2020).
- Aleksander Madry et al. 2018. Towards Deep Learning Models Resistant to Adversarial Attacks. In ICLR.
- Stefano Markidis. 2023. Programming Quantum Neural Networks on NISQ Systems: An Overview of Technologies and Methodologies. Entropy (2023).
- Keiron O’Shea and Ryan Nash. 2015. An introduction to convolutional neural networks. CoRR abs/1511.08458 (2015).
- Waseem Rawat and Zenghui Wang. 2017. Deep convolutional neural networks for image classification: A comprehensive review. Neural computation (2017).
- Quantum support vector machine for big data classification. Physical review letters (2014).
- Evaluating accuracy and adversarial robustness of quanvolutional neural networks. In CSCI.
- Adversarial robustness in hybrid quantum-classical deep learning for botnet dga detection. Journal of Information Processing 30 (2022), 636–644.
- Maxwell T West et al. 2023. Benchmarking adversarially robust quantum machine learning at scale. Physical Review Research (2023).
- Han Xiao et al. 2017. Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms. CoRR abs/1708.07747 (2017). http://arxiv.org/abs/1708.07747
- Kamila Zaman et al. 2023. A Survey on Quantum Machine Learning: Current Trends, Challenges, Opportunities, and the Road Ahead. CoRR abs/2310.10315 (2023).
- Wang Zhiqiang and Liu Jun. 2017. A review of object detection based on convolutional neural network. In 2017 36th Chinese control conference (CCC).
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.