The field of smart infrastructure is witnessing significant advancements in cybersecurity and predictive modeling. Researchers are focusing on developing innovative solutions to detect and mitigate cyber threats, as well as improve the accuracy of predictive models for energy demand and water distribution systems. The integration of machine learning, blockchain, and digital twins is becoming increasingly popular, enabling more secure and efficient management of smart infrastructure. Noteworthy papers in this area include:

• A Virtual Cybersecurity Department for Securing Digital Twins in Water Distribution Systems, which proposes an affordable and automated framework for small and medium-sized enterprises to secure their water systems.
• Smart Water Security with AI and Blockchain-Enhanced Digital Twins, which presents an integrated framework for secure and transparent water management using LoRaWAN-based data acquisition, machine learning-driven Intrusion Detection System, and blockchain-enabled Digital Twin platform.
• The Dark Side of Digital Twins: Adversarial Attacks on AI-Driven Water Forecasting, which highlights the vulnerability of machine learning models to adversarial attacks and emphasizes the need for robust defenses.
• Validation of a 24-hour-ahead Prediction model for a Residential Electrical Load under diverse climate, which proposes a global model for 24-hour-ahead hourly electrical energy demand prediction that performs effectively across diverse climate conditions and datasets.