Cyber Attack Detection Using Deep Learning

The rapid growth and increasing sophistication of cyberattacks-such as SQL injection, cross-site scripting (XSS), and distributed denial-of-service (DDoS) attacks-pose serious challenges to conventional rule-based cybersecurity solutions. This research presents an intelligent deep learning-based cyberattack detection framework designed to overcome the limitations of traditional systems. Two complementary approaches are proposed: one for detecting SQL injection and XSS attacks in web traffic, and another for identifying DDoS attacks in network environments. By combining advanced preprocessing, Word2Vec-based feature extraction, feature selection using Extra Trees, and a hybrid CNN-LSTM model, the proposed system effectively captures both spatial and temporal attack patterns. Extensive evaluations on multiple benchmark datasets, including CICIDS2018, CICDDoS2019, HTTP CSIC 2010, and custom testbed datasets, demonstrate significant performance improvements over existing methods, highlighting the effectiveness and robustness of the proposed approach for modern cyberattack detection.