Please use this identifier to cite or link to this item:
|Title||An Approach for Detecting and Preventing DoS Attacks in LAN|
|Title in Arabic||الية اكتشاف ومنع هجوم الحرمان من الخدمة في الشبكات المحلية|
Nowadays, Denial of service (DoS) attacks, have become a major security threat to networks and to the Internet, DoS is harmful to the networks as it delays legitimate users from accessing the server, usually services such as in the Medical field, E-business field, etc. are out. In critical cases, may cause the server shut down, wasting valuable resources, therefore, leading to financial loss and in worst cases, loss of patient life due to delays in medical tests. Moreover, the DoS detection problem is complex because attackers always invent new methods that can't be recognized easily, so many traditional approaches were used, such as, intrusion detection to detect intrusions through their signatures, but these techniques were unable to protect networks and servers before the appearance of their signatures. In general, some researches were done to detect and prevent DoS from occurring in a wide area network (WAN), but fewer researches were done on Local Area Network (LAN) to detect and prevent DoS attacks, and therefore increasing network security, yet, detecting and preventing DoS attacks is still a challenging task, especially in LAN. In this research, we proposed an approach using data mining techniques by combination of classifiers (decision tree and k-nearest neighbor) to detecting and preventing DoS attacks. Our work is based on European Gaza Hospital (EGH) Dataset that is collected from EGH network, then Labeled dataset manually. In addition preprocessing and processing stages, our approach is implemented using Rapidminer and exploits data mining algorithms to identify DoS attacks. The experimental results showed that the proposed approach is effective in identifying DoS attacks, our designed approach achieves significant results. In the average case, our accuracy is up to 99.96%, we used defense mechanism and compared our approach with other approaches, and we found that our approach achieved best results in accuracy.
|Publisher||الجامعة الإسلامية - غزة|
|Files in this item|