N-Gram-Based Detection of New Malicious Code

The current commercial anti-virus software detects a virus only after the virus has appeared and caused damage. Motivated by the standard signature-based technique for detecting viruses, and a recent successful text classification method, we explore the idea of automatically detecting new malicious code using the collected dataset of the benign and malicious code. We obtained accuracy of 100% in the training data, and 98% in 3-fold cross-validation.

• Type: Conference
• Year: 2004
• Where: COMPSAC
• Authors: Tony Abou-Assaleh, Nick Cercone, Vlado Keselj, Ray Sweidan
• Keywords: Commercial Anti-virus Software, COMPSAC 2004, Malicious Code, Software Engineering, Successful Text Classification