Full Program

Feature-Enhanced Deep Learning Models for Cyber-Physical System Security

Summary:

Abstract - The growing reliance on cyber-physical systems (CPS) in critical infrastructure has highlighted the need for accurate and efficient intrusion detection methods. Traditional anomaly detection techniques struggle to handle the complexity and variability of CPS data often resulting in high false-positive rates. This study investigates the use of genetic algorithms (GA) with dynamic thresholding as a feature selection method to improve the performance of deep learning models Three publicly available CPS datasets were used to validate the approach including the water distribution testbed (WDT) power system and gas pipeline datasets. Deep learning models including LSTM CNN and Autoencoders were enhanced with techniques such as attention mechanisms evolving filters and GA-based weight pruning. Results show the hybrid CNN model with GA optimization had the second highest performance The evolving filter model demonstrated strong potential with further tuning. Overall the integration of GA-driven optimization significantly boosted model accuracy and reduced loss

Author(s):

Javeyon Vaughn    
North Carolina A&T State University
United States

Kaushik Roy    
North Carolina A&T State University
United States

Yaa Acquaah    
North Carolina A&T State University
United States