Search results:
Found 2
Listing 1 - 2 of 2 |
Sort by
|
In modern years, internet and computers were used by many nations all overhead the world in different domains. So the number of Intruders is growing day-by-day posing a critical problem in recognizing among normal and abnormal manner of users in the network. Researchers have discussed the security concerns from different perspectives. Network Intrusion detection system which essentially analyzes, predicts the network traffic and the actions of users, then these behaviors will be examined either anomaly or normal manner. This paper suggested Deep analyzing system of NIDS to construct network intrusion detection system and detecting the type of intrusions in traditional network. The performance of the proposed system was evaluated by using Kdd cup 99 dataset. The experimental results displayed that the proposed module are best suited due to their high detection rate with false alarm rate.
في السنوات الأخيرة، وقد استخدمت الإنترنت وأجهزة الكمبيوتر من قبل العديد من الناس في جميع أنحاء العالم في العديد من المجالات. وبالتالي فإن عدد المتسللين يتزايد يوما بعد يوم مما يشكل مشكلة حرجة في التمييز بين السلوك الطبيعي وغير طبيعي من المستخدمين في الشبكة. وقد ناقش الباحثون المخاوف الأمنية من وجهات نظر مختلفة. نظام كشف التسلل الشبكي الذي أساسا يحلل ، ويتنبأ حركة مرور الشبكة وسلوكيات المستخدمين، ثم سيتم فحص هذه السلوكيات إما هجوم أو سلوك طبيعي. اقترحت هذه الورقة نظام تحليل عميق لبناء شبكة نظام كشف تطفل شبكي والكشف عن نوع التطفل في الشبكة التقليدية. تم تقييم اداء النظام المقترح باستخدام kdd cup 99 . أظهرت النتائج ان النموذج المقترح هو الانسب نظرا لمعدل كشف تطفل عالي مع نسبة انذار كاذبة منخفضة.
Network intrusion detection system --- data mining --- False alarm --- Decision Tree algorithm --- Self-organizing map algorithm
Nowadays, Security of network traffic is becoming a major issue ofcomputer network system according to the huge development of internet.Intrusion detection system has been used for discovering intrusion and tomaintain the security information from attacks. In this paper, produced twolevels of mining algorithms to construct Network Intrusion Detection System(NIDS) and to reduce false alarm rate, in the first level Naïve Bayes algorithmis used to classify abnormal activity into the main four attack types fromnormal behavior. In the second level ID3 decision tree algorithm is used toclassify four attack types into (22) children of attacks from normal behavior.To evaluate the performance of the two proposed algorithms by using kdd99dataset intrusion detection system and the evaluation metric accuracy,precision, DR, F-measure. The experimental results prove that the proposalsystem done high detection rates (DR) of 99 % and reduce false positives (FP)of 0 % for different types of network intrusions
data mining --- intrusion detection system --- false alarm --- Decision Tree classifier --- Naïve Bayes classifier..
Listing 1 - 2 of 2 |
Sort by
|