SELECTING MOST SUITABLE INTRUSION DETECTION METHOD USING SEMANTIC-BASED ONTOLOGY MODEL
Seminar Date: Wednesday June 14 12:00pm
Brief abstract: Building ontology for wireless network intrusion detection is an emerging method for the purpose of achieving high accuracy, comprehensive coverage, self-organization for network security, and further developing intrusion detection decision support system (DSS). In the first part of our talk, we try to leverage the power of Natural Language Processing (NLP) and Crowdsourcing for this purpose by constructing lightweight semi-automatic ontology learning framework which aims at developing a semantic-based solution-oriented intrusion detection knowledge map using documents from Scopus. Our proposed framework relies on NLP as its automatic component while Crowdsourcing is initiated when it turns to the semi part. The main intention of applying both NLP and Crowdsourcing is to develop a semi-automatic ontology learning method in which NLP is used to extract and connect useful concepts while in uncertain cases human power is leveraged for verification. In the second part, we develop a scientometrics based method in order to evaluate the links in the developed intrusion detection ontology by assigning weight to the connections of the ontology. Since each link is constructed by one article, citation analysis method is applied as a basic model based on four determining indexes, and a novel model is proposed to repeat the basic model in the multiple levels of paper citation system. The two parts can be integrated into a knowledge-based solution-oriented intrusion detection DSS which will be able to provide a certain number of solutions or techniques proposed by famous scientists or researchers to detect different types of attacks, and also be capable of supplying suggestions on intrusion prevention methods. This research makes a high level of theoretical contribution meanwhile it is also of great practical value for the academic field as well as the network security industry.
Short Bio: Morteza Saberi is a postdoctoral fellow with School of Business, UNSW Canberra. He has an outstanding research records and significant capabilities in area of business intelligence, data mining and applied machine learning. He has published more than 150 papers in reputable academic journals and conference proceedings. His Google Scholar citations and h-index are 1550 and 19, respectively. He was a lecturer at the Department of Industrial Engineering at University of Tafresh. He won 35 national and international awards such as 2006–2012 Best Researcher of Young researcher Club, Islamic Azad University (Tafresh Branch), National Eminent Researcher Award among Young researcher Club, Islamic Azad University members, Best PhD Thesis Award at IEOM 2016, etc.