Identifying Suspicious URLs: An Application of Large-Scale Online Learning
Source: University of California
This paper explores online learning approaches for detecting malicious Web sites (those involved in criminal scams) using lexical and host-based features of the associated URLs. The authors show that this application is particularly appropriate for online algorithms as the size of the training data is larger than can be efficiently processed in batch and because the distribution of features that typify malicious URLs is changing continuously. Using a real-time system the authors developed for gathering URL features, combined with a real-time source of labeled URLs from a large Web mail provider, they demonstrate that recently developed online algorithms can be as accurate as batch techniques, achieving classification accuracies up to 99% over a balanced data set.