隨著網(wǎng)絡(luò)入侵技術(shù)的不斷發(fā)展, 入侵的行為表現(xiàn)出不確定性、復(fù)雜性、多樣性等特點(diǎn)，
入侵檢測(cè)面臨許多有待解決的關(guān)鍵問(wèn)題。本文詳細(xì)介紹了基于數(shù)據(jù)挖掘的入侵檢測(cè)系統(tǒng)的設(shè)計(jì)和具體實(shí)現(xiàn)，也就是用于數(shù)據(jù)預(yù)處理和分類(lèi)、聚類(lèi)挖掘的數(shù)據(jù)挖掘技術(shù)。在數(shù)據(jù)預(yù)處理中，我們使用基于屬性抽取的方法去除干擾屬性。最后，我們對(duì)系統(tǒng)進(jìn)行了測(cè)試，通過(guò)測(cè)試結(jié)果我們發(fā)現(xiàn)挖掘的效率和正確率，而系統(tǒng)確實(shí)能夠有效的檢測(cè)到已知未知攻擊。
關(guān)鍵字: 入侵檢測(cè)；數(shù)據(jù)挖掘；信息安全
Abstract: As the development of the network intrusion technology, the action of intrusion
represents variable, complicated, and uncertainty characteristic. Therefore, it faces so many
problems to resolve for intrusion detection. We introduce the design and implementation of the system which adopt the Data Mine technology of data pretreatment, classify and cluster patterns mine. We use the method based on features selection to get rid of noises. Finally, we give a test to the system. Through the test, we find that our intrusion detection system is efficient to detect known and unknown attack.
Keywords: Intrusion Detection; Data Mining; Information Security