Utilizing Machine Learning and Deep Learning Techniques for the Detection of Distributed Denial of Service (DDoS) Attacks

The growing number of cyber-attacks has heightened the need for robust security measures, as they escalate in frequency and impact, affecting both economic stability and personal safety. Traditional methods of detecting these cyber threats are often costly and slow, prompting the need for more efficient and accurate technologies. This study explores advanced artificial intelligence techniques, utilizing both Machine Learning (ML) and Deep Learning (DL), to enhance the detection of Distributed Denial of Service (DDoS) attacks, by integrating diverse AI methodologies, including deep neural networks, random forest, long short-term memory and extreme gradient boosting systems, moreover, the paper investigates their collective effectiveness on the CICIDS2017 dataset. The analysis confirms that these integrated AI approaches achieve significant accuracy, recall and low false positive rates in identifying DDoS incidents. The paper is constructed as follows, Section 1 – Introduction, Section 2 A review of AI methods, Section 3 - Evolution of proposed models, Section 4 Experimental results, and Sect. 5 Discusses possible areas for further research.