Information Trust Institute University of Illinois at Urbana-Champaign

Professor Han has done groundbreaking work in the area of data mining. The rise of data mining reflects the imminent needs of today's computerized, data-intensive society. Data mining is an exciting scientific discipline since it requires us to integrate and advance the knowledge produced in multiple disciplines, including database systems, statistics, machine learning, algorithms, information theory, spatial and multimedia databases, bioinformatics, Web technology, and high performance computing, among others.

Data mining has been used extensively to identify anomalous conditions that may occur in the event of bugs or intrusions, and Professor Han has been working on trust and security in systems by pushing the boundaries of data mining techniques. Two of his current projects address the issue of trust and data mining in two different ways.

With the SecureMine project, Professor Han's group is working on a secure data mining system that will take care of privacy and security issues in data mining.

Traditionally, data mining techniques have been applied to large but off-line warehouses of data. In the Stream Mine project, Professor Han and his students have developed algorithms that enable the efficient real-time data mining of streams of data. With NCSA they were able to implement the streaming algorithms in a proof-of-concept network intrusion detection system for the MAIDS project.

Recent trust-oriented publications from Jiawei Han include:

• Y. Dora Cai, David Clutter, Greg Pape, Jiawei Han, Michael Welge, and Loretta Auvil. MAIDS: Mining Alarming Incidents from Data Streams. Proceedings of the 23rd ACM SIGMOD (International Conference on Management of Data), Paris, France, June 13-18, 2004.
• C. Aggarwal, J. Han, J. Wang, and P. S. Yu. On Demand Classification of Data Streams. Proc. 2004 Int. Conf. on Knowledge Discovery and Data Mining (KDD'04), Seattle, WA, Aug. 2004.
• C. Giannella, J. Han, J. Pei, X. Yan, and P. S. Yu. Mining Frequent Patterns in Data Streams at Multiple Time Granularities, in H. Kargupta, A. Joshi, K. Sivakumar, and Y. Yesha (eds.), Next Generation Data Mining, MIT Press, 2003.
• X. Li, J. Han, and H. Gonzalez. High-Dimensional OLAP: A Minimal Cubing Approach. Proc. 2004 Int. Conf. on Very Large Data Bases (VLDB'04), Toronto, Canada, Aug. 2004.