AUTOENCODERLAR YORDAMIDA TARMOQ TRAFIGIDA ANOMALIYALARNI NAZORATSIZ ANIQLASH: NSL-KDD MA'LUMOTLAR TO'PLAMI ASOSIDA AMALIY TADQIQOT
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Belgilangan ma'lumotlarning cheklanganligi nazoratli o'qitish modellarining asosiy muammosi hisoblanadi. Ushbu tadqiqotda tarmoq trafigidagi anomaliyalarni aniqlash uchun autoencoder asosidagi nazoratsiz yondashuv taklif etiladi. NSL-KDD dataseti ustida o'tkazilgan eksperimentlar shuni ko'rsatdiki, model faqat normal trafik bilan o'qitilib, AUC-ROC 96.13% va Precision 96.25% ko'rsatkichlariga erishdi. Zero-day hujumlarning 40.22% imzosiz aniqlanishi autoencoderlarning an'anaviy signature-based tizimlarga nisbatan ustunligini tasdiqlaydi. Gibrid yondashuv eng samarali strategiya sifatida tavsiya etiladi.
Fields of Study & Subjects
Network Security and Intrusion Detection
Internet Traffic Analysis and Secure E-voting
Network Packet Processing and Optimization
Publication details
- Journal / source
- CyberLeninK (CyberLeninka)
- Publication date
- 26 March 2026
- Language
- UZ