Application-Layer DDoS Attack Detection Using Explicit Duration Recurrent Network-Based Application-Layer Protocol Communication Models

Existing application-layer distributed denial of service (AL-DDoS) attack detection methods are mainly targeted at specific attacks and cannot effectively detect other types AL-DDoS attacks. This study presents an protocol communication model for detection, based on the explicit duration recurrent network (EDRN). The proposed method includes training detection. In phase, output each observation sequence is updated in real time. sequences keywords time intervals between adjacent keywords. Protocol extracted their identification using regular expressions. Experiments conducted datasets collected from a campus CICDDoS2019 dataset. results experiments show that EDRN superior to several popular neural networks accuracy, F1, recall, loss values. achieves accuracy 0.996, F1 0.992, recall 0.993, 0.041 detecting HTTP DDoS further our can multiple comparison test, outperforms state-of-the-art approaches.