Research

My research is focused on information security and privacy solutions that benefit a large number of users in real-world scenarios. I use a data-driven approach that integrates multiple sources of information to provide cross-domain adversarial-resistant systems. Practicality and robustness are key components of these systems, using techniques such as meta-information synthesis, adversarial behavior emulation, and short-circuit evaluation. To date, I have addressed a number of challenges in this manner, specifically:

• Developing solutions for filtering low-quality information;
• Designing solutions for preventing leakage of sensitive information; and
• Supporting cross-domain applicability and adaption to adversarial evolution.

Publications -- papers published in this area respective to the above include:

• D. Wang, Danesh Irani, and C. Pu. A Social-Spam Detection Framework. In Conference on Email and Anti-Spam (CEAS'11). Perth, Australia, September 2011. [PDF]
• Danesh Irani, M. Balduzzi, D. Balzarotti, E. Kirda, and C. Pu. Reverse Social Engineering Attacks in Online Social Networks. In Detection of Intrusions and Malware & Vulnerability Assessment (DIMVA'11). Amsterdam, Netherlands, July 2011. [PDF]
• Danesh Irani, S. Webb, K. Li, and C. Pu. Modeling Unintended Personal Information Leakage from Multiple Online Social Networks. In IEEE Internet Computing special issue on Security and Privacy in Social Networks. 2011. [PDF]
• Q. Wu, Danesh Irani, C. Pu, and L. Ramaswamy. Elusive Vandalism Detection at Wikipedia: A Text Stability-based Approach. In Conference on Information and Knowledge Management (CIKM'10). Toronto ON, Canada, October 2010. [PDF]
• Danesh Irani, S. Webb, and C. Pu. Study of Trend-Stuffing on Twitter through Text Classification. In Conference on Email and Anti-Spam (CEAS'10). Seattle, WA, July 2010. [PDF]
• Danesh Irani, S. Webb, and C. Pu. Study of Static Classification of Social Spam Profiles in MySpace. In International AAAI Conference on Weblogs and Social Media (ICWSM'10). Washington, DC, May 2010. [PDF]
• Danesh Irani, S. Webb, Kang Li, and C. Pu. Large Online Social Footprints - An Emerging Threat. In International Symposium on Secure Computing (SecureCom'09). Vancouver, B.C., Canada, August 2009. [PDF]
• B. Byun, C. Lee, S. Webb, Danesh Irani, and C. Pu. An Anti-spam Filter Combination Framework for Text-and-Image Emails through Incremental Learning. In Conference on Email and Anti-Spam (CEAS'09). Mountain View, California, July 2009 [PDF]
• Danesh Irani, S. Webb, J. Giffin, and C. Pu. Evolutionary study of phishing. In Anti-Phishing Working Group eCrime Researchers Summit (eCrime'08). Atlanta, Georgia, October 2008. Received best paper award. [PDF]

Related publications:

• M. Nguyen, E. Omiecinski, L. Mark, and Danesh Irani. A Fast Randomized Method for Local Density-based Outlier Detection in High Dimensional Data. In International Conference on Data Warehousing and Knowledge Discovery (DaWaK'10). Bilbao, Spain, September 2010. [PDF]
• Q. Wu, C. Pu, and Danesh Irani. Cosmos: A Wiki Data Management System. GIT-CERCS-09-07. [PDF]
• C. Pu, A. Sahai, J. Parekh, G. Jung, J. Bae, Y. Cha, T. Garcia, Danesh Irani, J. Lee, and Q. Lin. An Observation-Based Approach to Performance Characterization of Distributed n-Tier Applications. In IEEE International Symposium on Workload Characterization (IWSM'07).