Рақамли технологияларнинг назарий ва амалий масалалари Volume 8 Issue 3 (2025) · pp. 94-100
Analysis of the Performance Metrics of Existing Datasets for DDoS Attack Detection
Рахматов, Ф.А., Холмуминов, О.Т.
Abstract
To effectively detect and prevent DDoS (Distributed Denial-of-Service) attacks, it is necessary to use various datasets. This article analyzes the most popular datasets for DDoS attack detection, including CIC-DDoS2019, NSL-KDD, UNSW-NB15, BoT-IoT, and CAIDA, evaluating their performance metrics. Each dataset is assessed based on attack types, size, real-time proximity, and usability. Furthermore, the accuracy and F1-score metrics of machine learning models on these datasets are compared. The results indicate that the CIC-DDoS2019 dataset is the most comprehensive and close to real-world scenarios, providing high performance with Random Forest and SVM algorithms. The study guides in selecting the optimal dataset and model combination for DDoS attack detection.
набор данныхмашинное обучениеDDoSCIC-DDoS2019KNNRandom ForestSVMSYN FloodUDP FloodHTTP Flood
Metadata source: the journal's OAI-PMH archive · Sindex does not store the full text; it links to the source.