Distributed Denial of Service Attacks Detection Using Support Vector Machine

作者：Ahmad Iftikhar^*; Abdullah Azween B; Alghamdi Abdullah S; Hussain Muhammad

来源：Information-An International Interdisciplinary Journal, 2011, 14(1): 127-134.

• Neural Network Intrusion Detection (NNID)
• Support Vector Machine (SVM)
• Cooperative Association for Internet Data Analysis (CAIDA)
• Distributed Denial of Service (DDOS)
• False Positive (FP)
• False Negative (FN)
• True Positive (TP)
• True Negative (TN)

Attacks on the networks are most important issues. Therefore, the prevention of such attacks is imperative. The hindrance of such attacks is exclusively dependent on their detection. The detection is a prime part of any security tool such as Intrusion Detection System (IDS), Intrusion Prevention System (IPS), Adaptive Security Alliance (ASA), check points and firewalls. A variety of intrusion detection approaches be present to resolve this severe issue but the main problem is performance. Therefore, in this paper, a model is proposed to overcome performance issues. In this model, support vector machine (SVM) and backpropagation neural network are applied on distributed denial of service (DDOS) attacks. The system uses sampled data form cooperative association for internet data analysis (CAIDA) dataset, an attack database that is a standard for evaluating the security detection mechanisms. The results and comparative studies indicate that the proposed mechanism demonstrate more accuracy in case of false positive, false negative and detection rate.

• 出版日期2011-1