期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2016
卷号：5
期号：9
页码：17143
DOI：10.15680/IJIRSET.2016.0509100
出版社：S&S Publications
摘要：The key objective of distributed denial of service attack is to compile the multiple systems across theinternet with infected agents and these agents are designed to and programmed to launch the packet flood. With theincrease in popularity of internet there are number of security issues and to handle these issues intrusion detectionsystem (IDS) and intrusion prevention systems (IPS) are employed. IDS and IPS system follows the two differentapproaches for detecting intruders: Signature based detection and anomaly based detection. Signature detectiontechnique is a method of searching the network traffic for a series of bytes or packet and then compares these packetsagainst a set of signatures from known malicious threats. The anomaly based detection technique is a concept of abaseline for the network behaviour. Baseline can be considered as description of the type of network behaviour that canbe accepted, any deviation from this baseline is considered as an anomaly. Therefore anomaly based intrusion detectionuses machine learning techniques to detect whether a packet is intrusive or non-intrusive. This paper provides asystematic review of machine learning techniques used in DDoS attack detection.
