GUEST EDITORIAL: INTELLIGENT NETWORK SECURITY AND SURVIVABILITY

We are living in a digital world consisting of a large number of computers and other equipment creating ubiquitous computer networks. Because most human activities depend on computer networks, security and survivability have become a major concern. This special issue focuses on research related to the application of computational intelligence techniques to improve security and survivability of computer networks. Accordingly, the current issue presents eight research articles dealing with recent aspects of the network security and survivability where intelligent methods play relevant roles. Six papers are related to network security, and two focus on network survivability. Sanz et al. focus on malicious applications for Android-based mobile devices. They present manifest analysis for malware detection in Android (MAMA), a new method that extracts several features from the Android manifest of the applications to build machine learning classifiers and detect malware. Rebollo-Ruiz and Graña present innovative identification of user groups by a graph coloring problem (GCP) solution on access to a company intranet enterprise resource planning (ERP) program. Group identification serves to verify and tailor user profiles, roles, and privileges. ERP logs allow generation of a social network graph without explicit processes by the users, avoiding personal biases. A GCP solution is achieved by a novel gravitational swarm approach. The work by Sánchez et al. aims at being one step toward the intrusion detection topic by studying the combination of clustering and visualization techniques. To do that, a hybrid intelligent intrusion detection system (IDS), based on visualization techniques, is upgraded by adding automatic response due to clustering methods. To check the validity of the proposed clustering extension, it was applied to the identification of different anomalous situations related to the simple network management network protocol by using real-life data sets. Different ways of applying neural projection and clustering techniques are studied for comparison purposes. A novel method for spam detection based on a combination of Bayesian filtering, signature trees, and data compression–based similarity is introduced in the work by Prilepok et al. This novel method sorts out problems with uncertainty of the Bayesian filter by using signature trees and data compression based similarity. Cybernetics and Systems: An International Journal, 44:467–468 Copyright # 2013 Taylor & Francis Group, LLC ISSN: 0196-9722 print=1087-6553 online DOI: 10.1080/01969722.2013.818448