SVM based system to detect machines engaged in distributed denial of service attack

In this research, we propose the design of an efficient automated system which can effectively learn from the patterns of malicious activities, in the form of distributed denial of service attack (DDoS) against web servers on the Internet, and subsequently offer potential victims protection against such attacks by banning such requests in advance. A DDoS attack is a form of attack in which the attacker arranges for multiple machines to flood a website with repeated requests, saturating its capacity so it is not able to offer services to its customers due to being overload with fake requests. eQuality offers DDoS protection to its customers and by applying the results of this research it will be able to significantly improve the quality of its service and reduce its cost both in term of manpower to detect and prevent attack patterns manually as well as in terms of bandwidth that is used to serve and mitigate malicious requests.

Faculty Supervisor:

Dr. Mark Bauer

Student:

Seyed Ahmad Hosseini Lavasani

Partner:

eQuality

Discipline:

Mathematics

Sector:

Information and communications technologies

University:

University of Calgary