Society has grown to rely on Internet services, where data and information are collected and stored in unprecedented volumes. The large and small enterprises collect data and information in various aspects such as: businesses, customers, human resources, products, and suppliers, which are opening the window of opportunities for malicious users and crooks. This paper presents cybercrime detection and prevention model by using Support Vector Machine (SVM) and Adaboost algorithm to detect and classify of malicious codes in Facebook dataset.
Boser, Guyon, and Vapnik in COLT-92 [1, 2] first introduced support Vector Machine (SVM) in 1992. Support vector machines (SVMs) are a set of related supervised learning methods deployed for regression and classification . The fundamentals of Support Vector Machines (SVMs) have been enhanced by Vapnik  and became popular due to many promising features such as: better empirical performance. SVMs can be considered as techniques, which use the hypothesis space of linear separators in a high dimensional feature space, trained with a learning algorithm from optimization theory that makes a learning bias, derived from statistical learning theory. The SVM technique was developed to design separating hyperplanes for classification problems (see Figure 1) . Boosting methods are used for solving the classification problems and give weak learners as an input and then try to make a strong learner as an output [6, 7]. AdaBoost, short form of adaptive boosting, is a machine-learning algorithm, introduced by Freund and Schapire . It is a meta-algorithm, and can be deployed with many other learning algorithms to improve their performance.
The rest of the paper is organized as follows. In section 2 represents data mining and machine learning techniques. In section 3 include technical details about SVM algorithms. In section 4 elaborate about AdaBoost and AdaSVM and connection between these two methods. The experimental results are given in section 5, which presents the effectiveness of AdaSVM over SVM algorithms. Section 6 is follow by a conclusion and future works.
For full text: click here
(Author: hanif – Mohaddes Deylami, Yashwant Prasad Singh