Extracting Association Patterns in Network Communications



Downloads per month over past year

Portela García-Miguel, Javier and García Villalba, Luis Javier and Silva Trujillo, Alejandra Guadalupe and Sandoval Orozco, Ana Lucila and Kim, Tai-hoon (2015) Extracting Association Patterns in Network Communications. Sensors, 15 (2). pp. 4052-4071. ISSN 1424-8220

[thumbnail of sensors-15-04052.pdf]
Creative Commons Attribution.


Official URL: https://doi.org/10.3390/s150204052


In network communications, mixes provide protection against observers hiding the appearance of messages, patterns, length and links between senders and receivers. Statistical disclosure attacks aim to reveal the identity of senders and receivers in a communication network setting when it is protected by standard techniques based on mixes. This work aims to develop a global statistical disclosure attack to detect relationships between users. The only information used by the attacker is the number of messages sent and received by each user for each round, the batch of messages grouped by the anonymity system. A new modeling framework based on contingency tables is used. The assumptions are more flexible than those used in the literature, allowing to apply the method to multiple situations automatically, such as email data or social networks data. A classification scheme based on combinatoric solutions of the space of rounds retrieved is developed. Solutions about relationships between users are provided for all pairs of users simultaneously, since the dependence of the data retrieved needs to be addressed in a global sense.

Item Type:Article
Uncontrolled Keywords:anonymity; mixes; network communications; statistical disclosure attack
Subjects:Sciences > Computer science > Networks
Sciences > Computer science > Telecommunication
Sciences > Statistics
ID Code:67812
Deposited On:15 Sep 2021 14:54
Last Modified:15 Sep 2021 15:00

Origin of downloads

Repository Staff Only: item control page