Publication Date

Fall 2013

Degree Type

Master's Project


Computer Science


Metamorphic malware changes its internal structure with each infection, while maintaining its original functionality. Such malware can be difficult to detect using static techniques, since there may be no common signature across infections. In this research we apply a score based on Singular Value Decomposition (SVD) to the problem of metamorphic detection. SVD is a linear algebraic technique which is applicable to a wide range of problems, including facial recognition. Previous research has shown that a similar facial recognition technique yields good results when applied to metamorphic malware detection. We present experimental results and we analyze the effectiveness and efficiency of this SVD-based approach.