Semantic-Enabled Internet Services

• GeoEcho: Inferring User Interests from Geotag Reports in Network Traffic
  N. Xia, S. Miskovic, M. Baldi, A. Kuzmanovic, and A. Nucci
  In IEEE/WIC/ACM International Conference on Web Intelligence, Warsaw, Poland, August 2014 (Best Paper Award)
  [ .pdf | .pdf.gz | slides | review | press ]
  How one can utilize geotag beacons from your phone to understand your inerests.


• Mosaic: Quantifying Privacy Leakage in Mobile Networks
  N. Xia, H. Song, Y. Liao, M. Iliofotou, A. Nucci, Z. Zhang, and A. Kuzmanovic
  In Proceedings of ACM SIGCOMM 2013, Hong Kong, China, August 2013.
  [ .pdf | .pdf.gz | slides | review ]
  How to utilize OSN IDs and other identifiers to attribute significant amounts of traffic to individual users in mobile networks.


• Searching for Spam: Detecting Fraudulent Accounts Via Websearch
  M. Flores and A. Kuzmanovic
  Proceedings of the 14th International Conference on Passive and Active Measurement, Hong Kong, China, March 2013.
  [ .pdf | .pdf.gz | slides | review ]
  A method for detecting fraudulent accounts on Twitter by measuring web presence via websearch.


• Characterization of Vision-aided Indoor Localization and Landmark Routing
  A. Ballew, S. Srivastava, N. Valtchanov, C.-C. Lee, and A. Kuzmanovic
  In Proceedings of The Sixth International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS-2012), Palermo, Italy, July 2012.
  [ .pdf | .pdf.gz | .ppt | review ]
  A characterization of indoor localization with vision-aid.


• Understanding Human Movement Semantics: A Point of Interest Based Approach
  I. Trestian, K. Huguenin, L. Su, and A. Kuzmanovic
  Poster paper in Proceedings of WWW 2012, Lyon, France, April 2012.
  [ .pdf | .pdf.gz | poster | review ]
  A short paper describing how one can understand human movement characteristics by considering the influence of points of interest.


• Understanding Crowds' Migration on the Web
  Y. Wang, K. Pal, and A. Kuzmanovic
  In IEEE/WIC/ACM International Conference on Web Intelligence, Lyon, France, August 2011.
  [ .pdf | .pdf.gz | .ppt | review ]
  A large-scale analysis on how users' interests collectively spread on the Web.


• Towards Street-Level Client-Independent IP Geolocation
  Y. Wang, D. Burgener, M. Flores, A. Kuzmanovic, and C. Huang
  In Proceedings of USENIX NSDI 2011, Boston, MA, March 2011.
  [ .pdf | .pdf.gz | .ppt | video | review | press ]
  The paper presents a method for geolocating IP addresses with extreme accuracy.


• Extracting User Web Browsing Patterns from Non-Content Network Traces: The Online Advertising Case Study
  G. Macia, Y. Wang, R. Rodriguez, and A. Kuzmanovic
  In Journal of Computer Networks, to appear, 2011.
  [ .pdf | .pdf.gz | review ]
  An extended version of the INFOCOM 2010 paper.


• ISP-Enabled Behavioral Ad Targeting without Deep Packet Inspection
  G. Macia, Y. Wang, R. Rodriguez, and A. Kuzmanovic
  In Proceedings of IEEE INFOCOM 2010, San Diego, CA, March 2010.
  [ .pdf | .pdf.gz | .ppt | review | press ]
  The paper explains how ISPs can generate accurate user profiles and perform behavioral ad targeting without inspecting the packet payload.


• Measuring Serendipity: Connecting People, Locations and Interests in a Mobile 3G Network
  I. Trestian, S. Ranjan, A. Kuzmanovic, and A. Nucci
  In Proceedings of USENIX/ACM SIGCOMM Internet Measurement Conference (IMC'09), Chicago, IL, November 2009.
  [ .pdf | .pdf.gz | .ppt | review ]
  The paper performs a large scale study of application usage and mobility across a large metropolitan area.


• Googling the Internet: Profiling Internet Endpoints via the World Wide Web
  I. Trestian, S. Ranjan, A. Kuzmanovic, and A. Nucci
  In IEEE/ACM Transactions on Networking, to appear, August 2009.
  [ .pdf | .pdf.gz | review/response ]
  An extended version of the SIGCOMM 2008 paper.


• Unconstrained Endpoint Profiling (Googling the Internet)
  I. Trestian, S. Ranjan, A. Kuzmanovic, and A. Nucci
  In Proceedings of ACM SIGCOMM 2008, Seattle, WA, August 2008.
  [ .pdf | .pdf.gz | .ppt | review ]
  How you can use Google to profile Internet endpoints.