Svetlana Radosavac


I am a research scientist with background in network security, wireless networks, social network analysis and machine learning. My current interests lie in the areas of cyber security, application of graph databases to fraud detection and security threats and social network analysis.

I received my M.Sc. and Ph.D. from the University of Maryland, College Park, in 2002 and 2007 respectively, and my B.Sc. (5 year degree) from University of Belgrade, Serbia, in Electrical and Computer Engineering in 1999. For a brief period of time after completing my PhD I was a post-doctoral researcher with Institute for Systems Research at University of Maryland.

After completing graduate studies, I joined DOCOMO Innovations in Palo Alto, CA, where I worked on a wide range of projects spanning areas of security, wireless networking, machine learning, social networks, content distribution in mobile networks etc. I am currently with Fair Isaac Corporation (FICO), where I have been a part of the Cyber Analytics team, working on development of a model for detecting a wide range of security threats using a combination of self-learning analytics and anomaly detection techniques. More details HERE (The Wall Street Journal) and HERE. I also worked on applying graph databases for credit card fraud detection.

For a more detailed description of my interests please, check out Projects and Publications. You can also check out my Google scholar profile.


  • Cyber Security
  • Data Analysis
  • Machine Learning
  • Social Network Analysis
  • Mobile networks
  • Game theory
  • Behavioral economics
  • Cyber crime


  • Python and Python scientific libraries (expert), Java (basic)
  • Machine learning packages: scikit-learn, nltk
  • Big data tools: Spark, Hadoop, Pig
  • Graph databases: Neo4j (expert) and Titan (basic)


My interests span the areas of cyber security, data science, machine learning and mobile networks. My current work is in the area of cyber security and Big Data. I also have experience in the area of graph databases and applications on fraud and anomaly detection. I am interested in working in the areas of network security, social network analysis and graph databases with application to fraud detection.


  • S. Radosavac, U. Kozat and J. Kempf, “On the Use of Admission Control to prevent DDoS Attacks on Mobile Networks”, submitted to Transactions on Mobile Computing
  • H. Sharara, C. Westphal, S. Radosavac and U. C. Kozat, “Utilizing Social Influence in Content Distribution Networks” in Proceedings of IEEE ICC-2011, Kyoto, Japan, 2011 (best paper award)
  • A. A. Cardenas, S. Radosavac and J. S. Baras, “Evaluation of Detection Algorithms for MAC Layer Misbehavior: Theory and Experiments”, IEEE/ACM Transactions on Networking (ToN), Pages 605-617, Vol. 17, Issue 2. April 2009.
  • S. Radosavac, G. V. Moustakides, J. S. Baras and I. Koutsopoulos, “An analytic framework for modeling and detecting access layer misbehavior in wireless networks”, ACM Transactions on Information and System Security (ACM TISSEC), Vol. 11, No. 4, July 2008.
  • J. Grossklags, S. Radosavac, A. Cardenas, J. Chuang, “Nudge: Intermediaries’ Role in Interdependent Network Security” Proceedings of 3rd International Conference on Trust and Trustworthy Computing (Trust’10), June 2010.