Exploring quantum machine and deep learning for malware detection

This project aims to enhance malware detection capabilities through the use of quantum neural networks (QNNs) and quantum machine learning (QML), leveraging quantum computing principles for superior performance compared to classical neural networks. As cyber threats become increasingly sophisticated, QNNs and QML present promising opportunities for breakthroughs in identifying and analyzing malicious activities.
We will implement QNN models using open-source quantum computing frameworks, enabling us to explore the unique advantages of quantum computing, which may lead to more efficient data processing. The project will involve curating diverse malware datasets, ensuring coverage of various types of malware and attack vectors, followed by necessary preprocessing to prepare the data for training.
Once the datasets are ready, we will train the QNN models while experimenting with different architectures and hyperparameters to optimize performance. We will then compare the performance of the QNN models against classical methods using metrics such as accuracy, precision, recall, and F1-score. Ultimately, this project aims to demonstrate how QNNs and QML can significantly improve current malware detection techniques, integrating these advancements into existing cybersecurity frameworks to enhance resilience against evolving cyber threats.

Faculty Supervisor:

Fadoua Khennou

Student:

Partner:

Cadi Ayyad University

Discipline:

Computer science

Sector:

Education

University:

Université de Moncton

Program: