Automated signature generation for Zero-day polymorphic worms using a Double-honeynet
Mohssen M. Z. E. Mohammed · Open University of Cape Town (University of Cape Town) · 2012
This thesis proposes an accurate system for signature generation for Zero-day polymorphic worms. Thesis consists of two parts: In part one, polymorphic worm instances are collected by designing a novel Double-honeynet system, which is able to detect new worms that have not been seen before. Unlimited honeynet outbound connections are introduced to collect all polymorphic worm instances. Therefore this system produces accurate worm signatures. In part two, signatures are generated for the polymorphic worms that are collected by the Double-honeynet system. Both a Modified Knuth-Morris-Pratt (MKMP) Algorithm, which is string matching based, and a Modified Principal Component Analysis (MPCA), which is statistics based, are used.