Distributed Denial of Service (DDoS) attack detection remains a challenging problem in cybersecurity. In DDoS, a network of compromised devices is used to overwhelm a target with a flood of requests, making it unable to serve legitimate requests. Recently, we have witnessed increasing interest in DDoS detection using machine learning (ML) and deep learning (DL) algorithms. ML/DL can improve the detection accuracy, but they can still be evaded through the use of ML/DL techniques in the generation of the attack traffic. In this talk, we will discuss DDoS attacks, their impacts, and detection solutions. We will also present a DDoS detection method based on Long Short-Term Memory (LSTM) and explain how a GAN model generator can create DDoS traffic that closely matches the DDoS instances from our dataset, making it appear similar to benign traffic. Additionally, we will explain how to enhance this approach to detect adversarial DDoS attacks.