A Novel Light Weighted Feature ExtractionModel for Web Defacement Intrusion Detection

Wide spread use of websites in the cyber-spacealong with their availability in the public domain hasincreased the cyber attacks against these platforms.Defacement attack which results in the variation of the websiteappearance is a common attack launched againstorganizational websites for some motivations. In this paper, tomonitor a website against defacement attack, a machinelearning- based approach is proposed. From the continent ofthe website, a number of features related to text, tags and linksare extracted and investigated. In the case of any indication ofdefacement attack, to evaluate the appearance of the website,its screenshot is taken and fed to a convolutional neuralnetwork for final decision. This network is trained using wellknownavailable data sets. Results demonstrate theeffectiveness of the proposed defacement detection methodwith an accuracy rate of ۹۹.۸%.