SafeBrowsingCloud: Detecting Drive-by-Downloads Attack Using Cloud Computing Environment

Abstract

Drive-by downloads attack has become the primary attack vehicle for malware distribution in recent years. One existing method of detecting drive-by download attacks is using static analysis technique. However, static detection methods are vulnerable to sophisticated obfuscation and cloaking. Dynamic detection methods are proposed to overcome the shortcomings of static analysis techniques and can get a higher detection rate. But dynamic anomaly detection methods are typically resource intensive and introduce high time overhead. To improve performance of dynamic detection techniques, we designed SafeBrowingCloud, a system based on apache S4, a distributed computing platform. And the system is deployed at edge router. SafeBrowingCloud analyzes network traffic, executes webpages in firefox with modified javascript engine, abstracts javascript strings and detects shellcode with three shellcode detection methods to find malicious web pages. Experimental results show efficiency of the proposed system with the high-speed network traffic.