This paper explores the detection of Distributed Denial-of-Service (DDoS) attacks using a combination of evolutionary optimization algorithms and machine learning techniques. The authors propose three methods—XGB-GA, RF-GA, and SVM-GA—integrated with Tree-based Pipelines Optimization Tool (TPOT) and genetic programming. The study uses datasets related to DDoS attacks to train machine learning models based on XGB, RF, and SVM algorithms, employing 10-fold cross-validation. The models are further optimized using evolutionary algorithms, achieving high accuracy scores: 99.99% with XGB-GA, 99.50% with RF-GA, and 99.99% with SVM-GA. TPOT is used to identify the optimal algorithm for constructing the machine learning model, with the genetic algorithm selecting XGB-GA as the most effective choice. The research advances the field of DDoS attack detection by presenting a robust and accurate methodology, enhancing cybersecurity and fortifying digital infrastructures against these pervasive threats.This paper explores the detection of Distributed Denial-of-Service (DDoS) attacks using a combination of evolutionary optimization algorithms and machine learning techniques. The authors propose three methods—XGB-GA, RF-GA, and SVM-GA—integrated with Tree-based Pipelines Optimization Tool (TPOT) and genetic programming. The study uses datasets related to DDoS attacks to train machine learning models based on XGB, RF, and SVM algorithms, employing 10-fold cross-validation. The models are further optimized using evolutionary algorithms, achieving high accuracy scores: 99.99% with XGB-GA, 99.50% with RF-GA, and 99.99% with SVM-GA. TPOT is used to identify the optimal algorithm for constructing the machine learning model, with the genetic algorithm selecting XGB-GA as the most effective choice. The research advances the field of DDoS attack detection by presenting a robust and accurate methodology, enhancing cybersecurity and fortifying digital infrastructures against these pervasive threats.