K. Maharana

Cyber-Physical Attack Detection in Water Distribution Systems Using a Hybrid Ensemble of XGBoost, Isolation Forest, and LSTM Autoencoder on the BATADAL Dataset

A three-model hybrid ensemble that combines a supervised XGBoost classifier, an unsupervised Isolation Forest with principal component analysis (PCA) dimensionality reduction, and an unsupervised LSTM Autoencoder trained on 24-hour sliding windows of sensor sequences provides rapid and reliable detection.