ABSTRACT
Encryption at the application layer is often promoted to protect privacy, i.e., to prevent someone in the network from observing users' communications. In this work we explore how to build a profile for a target user by observing only the names of the services contacted during browsing, names that are still not encrypted and easily accessible from passive probes. Would it be possible to uniquely identify a target user from a large population that accesses the same network?
Aiming at verifying if and how this is possible, we propose and compare three methodologies to compute similarities between users' profiles. We use real data collected in networks, evaluate and discuss performance and the impact of quality of data being used. To this end, we propose a machine learning methodology to extract the services intentionally requested by users, which turn out to be important for the profiling purpose. Results show that the classification problem can be solved with good accuracy (up to 94%), provided some ingenuity is used to build the model.
Supplemental Material
- I. Bermudez, M. Mellia, M. Munafò, R. Keralapura, and A. Nucci. 2012. DNS to the Rescue: Discerning Content and Services in a Tangled Web. In Proceedings of the IMC. ACM, 413--426. Google ScholarDigital Library
- M. Conti, L. V. Mancini, R. Spolaor, and N. V. Verde. 2016. Analyzing android encrypted network traffic to identify user actions. IEEE Transactions on Information Forensics and Security 11, 1 (2016), 114--125.Google ScholarDigital Library
- D. Giordano, S. Traverso, and M. Mellia. 2015. Exploring browsing habits of internauts: A measurement perspective. In Proceedings of the Asian Internet Engineering Conference. ACM, 54--61. Google ScholarDigital Library
- D. Herrmann, C. Banse, and H. Federrath. 2013. Behavior-based tracking: Exploiting characteristic patterns in DNS traffic. In Computers & Security, Vol. 39. Elsevier, 17--33. Google ScholarDigital Library
- M. Kumpošt and V. Matyáš. 2009. User profiling and re-identification: case of university-wide network analysis. In Proceedings of the TrustBus. Springer, 1--10. Google ScholarDigital Library
- L. Olejnik, C. Castelluccia, and A. Janc. 2012. Why Johnny can't browse in peace: On the uniqueness of web browsing history patterns. In Proceedings of the HotPETs.Google Scholar
- B. Saltaformaggio, H. Choi, K. Johnson, Y. Kwon, Q. Zhang, X. Zhang, D. Xu, and J. Qian. 2016. Eavesdropping on fine-grained user activities within smartphone apps over encrypted network traffic. In Proceedings of the WOOT16. ACM, 59--78. Google ScholarDigital Library
- Karen Sparck Jones. 1972. A statistical interpretation of term specificity and its application in retrieval. Journal of documentation 28, 1 (1972), 11--21.Google ScholarCross Ref
- J. Su, A. Shukla, S. Goel, and A. Narayanan. 2017. De-anonymizing Web Browsing Data with Social Networks. To appear in WWW. ACM. Google ScholarDigital Library
- M. Trevisan, A. Finamore, M. Mellia, M. Munafo, and D. Rossi. 2017. Traffic Analysis with Off-the-Shelf Hardware: Challenges and Lessons Learned. IEEE Communications Magazine 55, 3 (March 2017), 163--169. Google ScholarDigital Library
- L. Vassio, I. Drago, and M. Mellia. 2016. Detecting User Actions from HTTP Traces: Toward an Automatic Approach. In Proceedings of the TRAC. IEEE, 50--55.Google Scholar
- G. Xie, M. Iliofotou, T. Karagiannis, M. Faloutsos, and Y. Jin. 2013. Resurf: Reconstructing Web-Surfing Activity from Network Traffic. In Proceedings of the Networking. IEEE, 1--9.Google Scholar
Index Terms
- Users' Fingerprinting Techniques from TCP Traffic
Recommendations
A Discussion of Privacy Challenges in User Profiling with Big Data Techniques: The EEXCESS Use Case
BIGDATACONGRESS '13: Proceedings of the 2013 IEEE International Congress on Big DataUser profiling is the process of collecting information about a user in order to construct their profile. The information in a user profile may include various attributes of a user such as geographical location, academic and professional background, ...
Beyond-Accuracy Perspectives on Graph Neural Network-Based Models for Behavioural User Profiling
UMAP '22: Proceedings of the 30th ACM Conference on User Modeling, Adaptation and PersonalizationThe presented doctoral research aims to develop a behavioural user profiling framework focusing simultaneously on three beyond-accuracy perspectives: privacy, to study how to intervene on graph data structures of specific contexts and provide methods to ...
Assessing the Reliability of Facebook User Profiling
WWW '15 Companion: Proceedings of the 24th International Conference on World Wide WebUser profiling is an essential component of most modern online services offered upon user registration. Profiling typically involves the tracking and processing of users' online traces (e.g., page views/clicks) with the goal of inferring attributes of ...
Comments