2009 · 165 citations · 8 references
ComputingComputer ScienceCybersecurityComputer SecurityMachine LearningMalware AnalysisBrowser SecurityCode Obfuscation AnalysisMalware ClassificationWeb Application SecurityJavascriptJavascript SecurityMachine Learning For Malware ClassificationMalicious Script DetectionObfuscated Malware ClassificationObfuscation ClassificationVoting Classifiers
As the World Wide Web expands and more users join, it becomes an increasingly attractive means of distributing malware. Malicious javascript frequently serves as the initial infection vector for malware. We train several classifiers to detect malicious javascript and evaluate their performance. We propose features focused on detecting obfuscation, a common technique to bypass traditional malware detectors. As the classifiers show a high detection rate and a low false alarm rate, we propose several uses for the classifiers, including selectively suppressing potentially malicious javascript based on the classifier's recommendations, achieving a compromise between usability and security.
8
Engin Kirda, Christopher Kruegel, Giovanni Vigna et al. · 2006 · 294 citations
Detecting Malicious JavaScript Code in Mozilla
O. Hallaraker, Giovanni Vigna · 2005 · 139 citations
Charles Reis, John Dunagan, Helen J. Wang et al. · ACM Transactions on the Web · 2007 · 108 citations