Coot Optimization with Deep Learning-Based False Data Injection Attack Recognition

The recent developments in smart cities pose major security issues for the Internet of Things (IoT) devices. These directly result from inappropriate management protocols and their implementation by IoT gadget developers. Cyber-attackers take advantage such gadgets’ vulnerabilities through various attacks as injection Distributed Denial Service (DDoS) attacks. In this background, Intrusion Detection (ID) is only way to identify mitigate damage. advancements Machine Learning (ML) Deep (DL) models are useful effectively classifying cyber-attacks. current research paper introduces a new Coot Optimization Algorithm with Learning-based False Data Injection Attack Recognition (COADL-FDIAR) model environment. presented COADL-FDIAR technique aims false data To accomplish this, initially pre-processes input selects features help Chi-square test. detect classify attacks, Stacked Long Short-Term Memory (SLSTM) exploited study. Finally, COA algorithm adjusts SLTSM model’s hyperparameters accomplishes superior recognition efficiency. proposed was experimentally validated using standard dataset, outcomes were scrutinized under distinct aspects. comparative analysis results assured performance over other approaches maximum accuracy 98.84%.