Work

Detection and mitigation strategies for cyber-attacks in offshore oil and gas industrial networks

Year: 2024
Type: dissertation
Abstract: Industrial Cyber-Physical Systems (ICPS) increasingly rely on insecure protocols, raising security concerns in oil and gas (OG) operations. Replacing these protocols is often too \nexpensive, highlighting the need for efficient cyber-attack detection. This thesis addresses this critical challenge by proposing a novel unsupervised anomaly detection model attack detection in OG environments. \n \nExisting Intrusion Detection Systems (IDS) for industrial networks, primarily Machine Learning (ML)-based, often suffer from high false positive rates and limited focus on \nOG environments. This potentially hinders real-world adoption. To address this gap, we introduce the Sliding Time-window Anomaly Detection (STADe) model – a novel \napproach that leverages the inherent periodicity of industrial network traffic for anomaly detection. \n \nThe STADe model segments network packet inter-arrival times into time windows and analyzes periodicity within each window. This approach demonstrably reduces False Discovery \nRates (FDR) compared to existing methods. \n \nExperiments evaluate existing ML-based IDSs and leverage the findings to develop STADe. A dedicated gas wellhead monitoring testbed was designed to emulate real-world scenarios and facilitate data collection for attack simulations and analysis. Additionally, this research identifies a novel field flooding attack capable of disrupting critical OG processes. \n \nThis research emphasizes the significance of network traffic periodicity and demonstrates the effectiveness of anomaly detection models that leverage this characteristic.
Institution: Cardiff University
Language: English
Open Access status: green
OpenAlex ID: W6990344068
Cites: 175
Cited by: 6
Related to: 10