Volume 1 - Issue 4, November - December 2025

With the rapid advancement of technology, the use of Internet of Things (IoT) devices continues to increase in daily life. These devices provide convenience and efficiency for ordinary users, even without advanced technical knowledge. IoT technology is commonly used in home security systems, smart refrigerators, smart televisions, and many other connected appliances. While these internetenabled devices offer several advantages, they also create serious security concerns. Cyber attackers constantly search for new ways to exploit weaknesses in digital systems, and IoT devices are particularly vulnerable due to their large numbers and limited protection. This makes them ideal targets for large-scale cyberattacks, including Distributed Denial of Service (DDoS) attacks, where compromised devices are used Bots to overwhelm networks and services. services, ultimately disrupting their availability. In order to determine whether an attack has taken place within a network, a dependable and efficient detection mechanism is required. One of the most widely used approaches for this purpose is artificial intelligence, specifically Machine Learning (ML) and Deep Learning (DL), which assist in identifying and analysing cyber threats. ML models utilize structured data and algorithms to recognize patterns, make predictions, and detect abnormal behaviour within network traffic. The primary objective of this paper is to review selected research studies and publications related to DDoS detection in IoT-based networks using machine learning techniques. This work provides a comprehensive reference base for researchers seeking to define or expand their studies in this field.