Open Access

Fatemeh Stodt, Fabrice Theoleyre, Christoph Reich

• This study presents a novel approach for fortifying network security systems, crucial for ensuring network reliability and survivability against evolving cyber threats. Our approach integrates Explainable Artificial Intelligence (XAI) with an ensemble of autoencoders and Linear Discriminant Analysis (LDA) to create a robust framework for detecting both known and elusive zero-day attacks. We refer to this integrated method as AE-LDA. Our method stands out in its ability to effectively detect both known and previously unidentified network intrusions. By employing XAI for feature selection, we ensure improved interpretability and precision in identifying key patterns indicative of network anomalies. The autoencoder ensemble, trained on benign data, is adept at recognising a broad spectrum of network behaviours, thereby significantly enhancing the detection of zeroday attacks. Simultaneously, LDA aids in the identification of known threats, ensuring a comprehensive coverage of potential network vulnerabilities. This hybrid model demonstrates superior performance in anomaly detection accuracy and complexity management. Our results highlight a substantial advancement in network intrusion detection capabilities, showcasing an effective strategy for bolstering network reliability and resilience against a diverse range of cyber threats.