Title :
Improved malicious code classification considering sequence by machine learning
Author_Institution :
Sch. of Comput. Sci. & Eng., Univ. of Aizu, Aizu-Wakamatsu, Japan
Abstract :
Classification of malicious code by machine learning gives more flexible and adaptable prediction result than by existing approaches [1]. But the approach just can identify looks-like malicious code instead of real malicious one. In this research, a novel method to reduce the vagueness in the classification by machine learning to consider code sequence.
Keywords :
learning (artificial intelligence); pattern classification; support vector machines; SVM approach; code sequence; improved malicious code classification; machine learning; support vector machine; vagueness reduction; Accuracy; Educational institutions; Support vector machine classification; Syntactics; Training; Vectors; classification; machine learning; malicious Web code;
Conference_Titel :
Consumer Electronics (ISCE 2014), The 18th IEEE International Symposium on
Conference_Location :
JeJu Island
DOI :
10.1109/ISCE.2014.6884429