Search Results for early-attack-detection

Abstract

Smart universities constitute a complex environment in which thousands of Internet of Things (IoT) devices are interconnected, rendering them an increasingly attractive target for sophisticated cyberattacks. This study aims to design an integrated framework combining Artificial Intelligence (AI) and IoT technologies for the early detection of cyberattacks within smart university environments, employing machine learning and deep learning algorithms — namely Random Forest and a hybrid CNN-LSTM model — to classify network traffic and detect anomalous patterns in real time. The study adopted a descriptive-analytical approach supported by a field questionnaire administered to a sample of 150 participants from IT and network security personnel across universities. Results revealed excellent questionnaire reliability (Cronbach's Alpha = 0.927) and a strong positive correlation (r = 0.674) between cybersecurity awareness and AI detection effectiveness, alongside the superiority of the proposed model over traditional systems by an accuracy margin of approximately 25 percentage points (96.3% vs. 71.2%). The study recommends adopting a five-layer architectural framework integrating IoT devices, data processing, AI inference, attack detection, and real-time response layers as a viable model for deployment in Arab smart universities.