Skip to content

Dr. Kantarcioglu and Team Receive Best Application Paper Award at PAKDD’16

This past April, Dr. Murat Kantarcioglu, UT Dallas computer science professor, and Director of the UT Dallas Data Security and Privacy Lab, and one of his team’s research scientists, Dr. Yan Zhou, received the acclaimed Best Application Paper Award from the 20th Pacific Asia Conference on Knowledge Discovery and Data Mining (PAKDD’16) for their research paper titled, “Modeling Adversarial Learning as Nested Stackelberg Games.”

Drs. Kantarcioglu and Zhou’s research paper explores ways of developing more robust data mining techniques suitable for cyber security applications. In their paper, Drs. Kantarcioglu and Zhou tackle the challenges of multiple types of adversaries with a nested Stackelberg game framework. The research presented in the paper demonstrates the effectiveness of their framework with extensive empirical results on both synthetic and real data sets. They also demonstrate that the nested game framework offers more reliable defense against multiple types of attackers.

Dr. Kantarcioglu explained the research done in his paper saying, “Over the last few years, as a part of recently completed Army Research Office project with co-Principal Investigators Dr. Bowei Xi from Purdue University and Dr. Bhavani Thuraisingham from UT Dallas, we focused on developing data mining techniques suitable for adversarial application domains such as cyber security, fraud detection, homeland security, and so on. In the past there has been some work, including ours, to develop resilient data mining models against adversarial attacks; all of the previous work considered one type of adversary (e.g., one type of hacker). However, in our award winning paper,

Drs. Kantarcioglu and Zhou receiving the award for Best Application Paper at PAKDD'16.
Drs. Kantarcioglu and Zhou receiving the award for Best Application Paper at PAKDD’16.

we have developed a game theoretical data mining model that is resilient to multiple types of adversaries with different capabilities/tactics. We believe that such data mining techniques will enable us to build reliable, effective, and practical cyber security incident detection tools.” The paper has been published in the two-volume journal PAKDD 2016 Advances in Knowledge Discovery and Data Mining.

Dr. Kantarcioglu expressed his appreciation for the conference by saying, “PAKDD is one of the premier conferences in data mining research and this year was the 20th anniversary of the conference. We were delighted to see that our contributions in adversarial data mining was recognized with this significant award by the data mining community.”

The 20th PAKDD’16 conference took place this past April 19th to 22nd in the coastal city of Auckland, New Zealand. The Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD) is one of longest-established and leading international conferences in the areas of knowledge discovery and data mining (KDD). The conference provides an international forum for researchers, members of academia, and industry practitioners to share their new ideas, original research results and practical development experiences from all KDD-related areas, including data mining, data warehousing, machine learning, artificial intelligence, databases, statistics, knowledge engineering, visualization, decision-making systems and emerging applications.


The UT Dallas Computer Science program is one of the largest Computer Science departments in the United States with over 1,600 bachelor’s-degree students, more than 1,100 master’s students, 160 PhD students, and 80 faculty members, as of Fall 2015. With The University of Texas at Dallas’ unique history of starting as a graduate institution first, the CS Department is built on a legacy of valuing innovative research and providing advanced training for software engineers and computer scientists.

CS Department Holds Its Biennial Retreat on Lake Ray Hubbard
Dr. Ryan McMahan, Virtual Reality Researcher and CS Professor Wins NSF Career Grant
Department of Computer Science