02023nam a22001697a 4500999001700000100007700017245010500094260002700199300001000226520121500236650004901451856003301500942001101533952010301544952010301647952010301750  c68366d68363  aMs. Sanjha Rehman Memona22-METSN-04aSupervisor - Dr. Adnan Ahmed Arain  aDDOS (Distributed Denial-of -Service) Attack Detection Using Machine Learning Algorithms (ME Thesis)  aNawabshahbQUESTc2024  a103p.  aABSTRACT

Currently, the most severe type of cyberattack is distributed denial of service attack. The bandwidth and buffer size of the hosting server are restricted due to limitations on Its capacity to supply resources to approved clients. DoS and DDoS are significant threats to any genuine customer who uses network services. These types of attacks should be avoided. We will examine three common forms of DDoS attacks: ICMP Flood, TCP SYN Flood, and UDP Flood. Meanwhile, we will be working on machine learning techniques like K-Nearest Neighbors (KNN), Decision Tree (DT), Multi-layer Perceptron (MLP), and Logistic Regression (LR) that are used to differentiate between regular conditions and assaults. The set of data generated by KDD99 is utilized in experimental research. This dataset is used to train and evaluate machine learning algorithms, and the trained algorithms are verified. In this work, we will identify various DDoS attacks using various techniques and evaluate their performance. This is a Classification work. These DDoS detectors could be useful in the future. The current work is compared to alternative machine learning methods that are employed in denial-

of-service attacks.

xii  aDepartment of Telecommunication Engineering   uhttps://tinyurl.com/33hm5r7b  cTHESIS  00104070aRESEARCHbRESEARCHd2024-05-24l0pMP/88-1276r2024-05-24 00:00:00w2024-05-24yTHESIS  00104070aRESEARCHbRESEARCHd2024-05-24l0pMP/88-1277r2024-05-24 00:00:00w2024-05-24yTHESIS  00104070aRESEARCHbRESEARCHd2024-07-26l0pMP/91-1322r2024-07-26 00:00:00w2024-07-26yTHESIS