Malicious code detection with ML

Public presentation by Olof Mogren
on Wed. 03 May 2017 at 10:00-12:00 in room EDIT 3364
JavaScript has become a ubiquitous Web technology that enables interactive and dynamic Web sites. The widespread adoption, along with some of its properties allowing authors to easily obfuscate their code, make JavaScript an interesting venue for malware authors. In this survey paper, we discuss some of the difficulties in dealing with malicious JavaScript code, and go through some recent approaches to detect and classify malicious JavaScript code statically using machine learning methods.
View PDF

Introductory papers
  • P. Likarish, Obfuscated malicious javascript detection using classification techniques (International Conference on Malicious and Unwanted Software 2009)
  • Advanced papers
  • Junjie Wang, JSDC: A hybrid approach for javascript malware detection and classification, (ACM Symposium on Information, Computer and Communications Security, ACM, 2015)
  • Y. Wang, A deep learning approach for detecting malicious JavaScript code (Security and communication networks 2016)
  • Fork me on GitHub