Anomaly Detection Using Quantum Neural Networks
Laya Billinty Varra, Jagadeshwari Puttanapura, C. Kishor Kumar Reddy, Shikha Khullar, Ghita Lazrek, Jothi Paranthaman · 2025
Quantum Neural Networks (QNNs) offer a new paradigm that takes advantage of quantum computing principles to emulate and improve on the functional benefits offered by classical neural networks. This chapter offers a broad investigation on QNNs in the context of anomaly detection in important real-world settings such as cybersecurity, fraud detection in financial transactions, real-time medical diagnostics, and many more. This chapter will provide a general overview of QNNs, their theoretical background, advantages with respect to classical models, and application or implementation success in anomaly detection for high-dimensional, noisy and streaming data. The chapter will also cover architectures, training methodologies, and simulation platforms for QNNs, and also include case studies to demonstrate these concepts. Finally, it will address their limitations, challenges in practical implementations, and future research possibilities.