Jul 2026
Detection of Network Irregularities Using Machine Learning Techniques
The proposed BAT framework achieves superior classification accuracy of 96%, effectively combining feature-level attention with gradient-boosted ensemble learning to improve detection precision, reduce manual feature engineering, and handle diverse attack categories including DoS, Probe, R2L, and U2R.
M. Philip, T. Sindhu, Devu Sai Sathwika et al.
· Journal of The Institution o... · 0 citations