In this project, we explore how we can determine the similarity between two pieces of code snippets, one of which is obfuscated. Malware detection is a primary focus of this project. There are many malware detectors which perform well. But when the malware code is obfuscated by some carefully designed obfuscator the performance is not that good. Because the obfuscator changes the program content by adding fake source code, changing the variable name, changing the control flow, etc. without changing the program semantic.