Quantum machine learning improves cybersecurity threat detection accuracy
Quantum Machine Learning for Cybersecurity Applications: Simulation and Hardware Validation
Cryptography and Security
Summary
Detecting unusual cyber attacks can be hard, especially when computing power and data features are limited. The authors show that using small quantum computers together with classical methods helps detect tricky cyber threats better than classical methods alone. They tested this idea on two cybersecurity tasks and found that quantum models caught some attacks classical ones missed. They also ran their best quantum model on real quantum hardware, finding its performance consistent but affected by device noise. Their study suggests small quantum devices can help improve cybersecurity detection even when resources are limited.
What this means in practice
- •For cybersecurity teams: Use hybrid quantum-classical models to improve detection of subtle cyber attacks under resource constraints.
- •For network security engineers: Integrate small quantum processors running quantum SVM models for enhanced spam filtering accuracy with limited data features.
Authors
Zirui Zhu, Zisheng Chen, Xiangyang Li
Abstract
Under tight feature and compute budgets, classical threat detection pipelines often degrade on near-decision-boundary events. Small quantum processors are now available, but existing work inadequately shows whether quantum components improve end-to-end threat detection under the above resource constrained conditions. This paper tries to address this gap with a hybrid architecture that uses a compact multilayer perceptron layer to compress the information in data and then routes the processed features to a few qubit quantum heads implemented in quantum support vector machine (QSVM) and variational quantum circuit (VQC) models. On a simulation platform, we benchmark these hybrid models against classical models with comparable parameter budgets on two representative cybersecurity tasks, network intrusion detection on NSL-KDD dataset and spam filtering on Ling-Spam dataset. To validate their precision on real quantum hardware, we deploy the best 4-qubit QSVM model on an IBM Quantum device with noise-aware execution, evaluated on a smaller sub-dataset. In the results, shallow quantum heads consistently match, and on difficult near-boundary cases modestly reduce missed attacks and false alarms compared to classical models using the same features. Hardware validation results track the simulation behavior closely enough that the remaining gap is dominated by device noise rather than model design. Furthermore, we conduct adversarial attacks to test the robustness of one QSVM model. Taken together, the study shows that even on small, noisy devices, carefully engineered quantum components may function as competitive, budget-aware components in practical cyber threat detection applications.