Volltext-Downloads (blau) und Frontdoor-Views (grau)

Advancing Network Survivability and Reliability: Integrating XAI-Enhanced Autoencoders and LDA for Effective Detection of Unknown Attacks

  • 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.

Export metadata

Additional Services

Search Google Scholar


Author:Fatemeh StodtORCiDGND, Fabrice Theoleyre, Christoph ReichORCiDGND
Parent Title (German):20th International Conference on the Design of Reliable Communication Networks (DRCN), 6-9 May 2024, Montreal, Canada
Document Type:Conference Proceeding
Year of Completion:2024
Release Date:2024/06/04
Tag:Autoencoders; Cybersecurity; Network anomaly detection; Network reliability; Un-supervised learning
First Page:9
Last Page:16
Open-Access-Status: Closed Access 
Licence (German):License LogoUrheberrechtlich geschützt