State Compression and Quantitative Assessment Model for Assessing Security Risks in the Oil and Gas Transmission Systems
This addresses security vulnerabilities in critical industrial infrastructure like oil and gas pipelines, though it appears incremental as an augmentation to an existing framework.
The paper tackles security risk assessment in Oil and Gas Transmission SCADA systems by proposing a data quantization and state compression approach (DQSCA) that reduces detection time by 27.74-42.06% with minimal accuracy loss (2.45-4.45%), and a quantitative risk assessment model that lowers MAPE error rates by 59.80-73.72% compared to existing systems for various attacks.
The SCADA system is the foundation of the large-scale industrial control system. It is widely used in industries of petrochemistry, electric power, pipeline, etc. The natural gas SCADA system is among the critical infrastructure systems that have security issues related to trusted communications in transactions at the control system layer, and lack quantitative risk assessment and mitigation models. However, to guarantee the security of the Oil and Gas Transmission SCADA systems (OGTSS), there should be a holistic security system that considers the nature of these SCADA systems. In this paper, we augment our Security Awareness Framework with two new contributions, (i) a Data Quantization and State Compression Approach (DQSCA) that improves the classification accuracy, speeds up the detection algorithm, and reduces the computational resource consumption. DQSCA reduces the size of processed data while preserving original key events and patterns within the datasets. (ii) A quantitative risk assessment model that carries out regular system information security evaluation and assessment on the SCADA system using a deductive process. Our experiments denote that DQSCA has a low negative impact on the reduction of the detection accuracy (2.45% and 4.45%) while it reduces the detection time much (27.74% and 42.06%) for the Turnipseed and Gao datasets respectively. Furthermore, the mean absolute percentage error (MAPE) rate for the proposed risk assessment model is lower than the intrusion response system (Suricata) for the DOS, Response Injection, and Command Injection attacks by 59.80%, 73.72%, and 66.96% respectively.