SHAP-based intrusion detection in IoT networks using quantum neural networks on IonQ hardware

• Published in: Journal of parallel and distributed computing Vol. 204; p. 105133
• Main Authors: Rajkumar, K, Shalinie, S. Mercy
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.10.2025
• Subjects: Distributed-denial-of-service; Explainable AI; Internet-of-Things; Quantum neural network; Software defined networking; Internet-of-Things; Distributed-denial-of-service; Explainable AI; Quantum neural network; Software defined networking
• ISSN: 0743-7315
• DOI: 10.1016/j.jpdc.2025.105133

•Development of a Quantum-Enhanced Intrusion Detection Framework: We introduce a novel intrusion detection system that integrates Explainable AI (XAI) with Quantum Neural Networks (QNNs) to improve the detection of DDoS attacks in IoT networks. The integration of XAI enhances the interpretability of quantum-based predictions, ensuring that the decision-making process is both accurate and understandable.•Comprehensive Dataset Utilization and Performance Benchmarking: This study uses two datasets, CIC-IoT2022 and the Proposed SDN-DDoS24, to thoroughly evaluate the performance of the XAI-QNN model. The results demonstrate superior performance with the SDN-DDoS24 dataset, highlighting the model’s effectiveness in detecting DDoS attacks across different traffic patterns.•Enhanced Transparency and Feature Selection Accuracy: By incorporating XAI into the post-processing phase, this research improves the transparency of the model’s decision-making. After the QNN classifies network traffic, SHAP values are used to identify the most significant features, such as IP addresses, ports, and traffic patterns. This clear interpretation of feature contributions reduces the likelihood of misclassification and enhances the accuracy of attack detection in IoT networks.•Comparison with Traditional Methods: We perform a detailed performance evaluation comparing the proposed XAI-QNN framework with traditional deep learning and machine learning classifiers. Our results emphasize the advantages of XAI-QNN in terms of both accuracy and interpretability, making it a more reliable and transparent solution for enhancing IoT security. Securing IoT networks against cyber-attacks, especially Distributed Denial of Service (DDoS) attacks, is a growing challenge due to their ability to disrupt services and overwhelm network resources. This study introduces a novel post-processing methodology that integrates Explainable AI (XAI) with Quantum Neural Networks (QNN) to enhance the interpretability of DDoS attack detection. We utilize the CICFlowMeter tool for feature extraction, processing bidirectional network traffic data and generating up to 87 distinct features. Notably, the CICFlowMeter removes potentially tampered features such as IP addresses and ports to prevent manipulation, addressing the limitations associated with the use of these features in the presence of attackers. After a QNN generates expectation values for a given input, SHAP (SHapley Additive exPlanations) values are applied to interpret the contributions of individual features in the decision-making process. Although the QNN output indicates whether a network flow is benign or malicious, the quantum model's complexity makes it difficult to interpret. By using SHAP values, we identify which features such as IP addresses, ports, and traffic patterns significantly influence the QNN’s classification, providing human-understandable explanations for the model's predictions. For evaluation, we used the CIC-IoT 2022and proposed SDN-DDoS24 datasets, with SDN-DDoS24 outperforming others when integrated with the proposed methodology. The QNN was implemented on IonQ quantum hardware through Amazon Braket, achieving an expectation value of 0.98 with a low latency of 113 milliseconds, making it suitable for applications requiring both precision and speed. This study demonstrates that integrating XAI with QNN not only improves DDoS attack detection accuracy but also enhances transparency, making the model more trustworthy for real-world cybersecurity applications. By offering clear explanations of model behavior, the approach ensures that security experts can make informed decisions based on the quantum-enhanced detection system, improving its reliability and usability in dynamic network environments.