UNSUPERVISED ANOMALY DETECTION IN NETWORK TRAFFIC USING AUTOENCODERS: AN EMPIRICAL STUDY ON THE NSL-KDD DATASET

Turg'unaliyev, Shohruz

Al-Farg'oniy avlodlari · 2026-yil

Annotatsiya

The scarcity of labeled data remains a fundamental limitation of supervised learning models. This study proposes an autoencoder-based unsupervised approach for detecting anomalies in network traffic. Experiments conducted on the NSL-KDD dataset demonstrate that the model, trained exclusively on normal traffic, achieved an AUC-ROC of 96.13% and Precision of 96.25%. The detection of 40.22% of zero-day attacks without any signatures confirms the superiority of autoencoders over traditional signature-based systems. A hybrid approach is recommended as the most effective strategy.

Maqola ma’lumotlari
MualliflarTurg'unaliyev, Shohruz
JurnalAl-Farg'oniy avlodlari
Nashr sanasi2026-03-27
Son1
Betlar356-363
TilRus

Kalit so‘zlar

Autoencoder, network security, anomaly detection, unsupervised learning, zero-day attacks, NSL-KDD, deep learning, Intrusion Detection System (IDS)., Автоэнкодер, сетевая безопасность, обнаружение аномалий, обучение без учителя, атаки нулевого дня, NSL-KDD, глубокое обучение, система обнаружения вторжений (IDS)., Autoencoder, tarmoq xavfsizligi, anomaliyalarni aniqlash, nazoratsiz o‘qitish, zero-day hujumlar, NSL-KDD, chuqur o'qitish, Intruziyalarni aniqlash tizimi (IDS).

Ilmiy soha

Al-Farg'oniy avlodlari jurnalidan boshqa maqolalar

Al-Farg'oniy avlodlari — barcha maqolalar