Utilization Data Mining to Detect Spyware

Abstract

Malicious software (malware) is any software that gives partial to full control of your computer to do whatever the malware creator wants. Malware can be a virus, worm, Trojan, adware, spyware, root kit, etc.Spyware is a type of malware (malicious software) installed on computers that collects information about users without their knowledge. In the year 1956, Artificial Intelligence (AI) was established at Dartmuth College during a conference. The technology developed so much that it started involving many other branches of engineering such as electronics, robotics etc. This eventually led to much more complex and smart machinery involving Artificial Intelligence. With the development of malware detection systems and Artificial Intelligence, as a new technology for them, Artificial Intelligence has been applied in anti-virus engines. There are several AI approaches that applied in spyware detection systems such as Artificial Neural Networks, Heuristic Technology and Data Mining (DM) Technique. Heuristic-based Detection performs well against known Spyware but has not been proven to be successful at detecting new spyware. In this paper we focus on DM-based malicious code detectors using Breadth-First Search (BFS) approach, which are known to work well for detecting viruses and similar software. BFS is a strategy for searching in a tree when search is limited to essentially two operations: (a) visit and inspect a node of a tree; (b) gain access to visit the nodes that are neighbor to currently visited node. The BFS begins at a root node and inspect all the neighboring nodes. Then for each of those neighbor nodes in turn, it inspects their neighbor nodes which were unvisited, and so on.