Injecting uncertainty in graphs for identity obfuscation

Abstract

Data collected nowadays by social-networking applications create fascinating opportunities for building novel services, as well as expanding our understanding about social structures and their dynamics. Unfortunately, publishing socialnetwork graphs is considered an ill-advised practice due to privacy concerns. To alleviate this problem, several anonymization methods have been proposed, aiming at reducing the risk of a privacy breach on the published data, while still allowing to analyze them and draw relevant conclusions.In this paper we introduce a new anonymization approach that is based on injecting uncertainty in social graphs and publishing the resulting uncertain graphs. While existing approaches obfuscate graph data by adding or removing edges entirely, we propose using a finer-grained perturbation that adds or removes edges partially: this way we can achieve the same desired level of obfuscation with smaller changes in the data, thus maintaining higher utility. Our experiments on real-world networks confirm that at the same level of identity obfuscation our method provides higher usefulness than existing randomized methods that publish standard graphs.

Personalized PageRank in Uncertain Graphs with Mutually Exclusive Edges

“…e uncertain edge e− (3) captures a form of uncertainty with mutual exclusion among the edges from i to d , e , or f . is uncertainty, however, is independent from the existence uncertainty of e− (2) . erefore, the proposed model allows as a special case the independent existence uncertainty model considered by many of the existing works [2,10,16,20,26,29].…”

“…An uncertain edge e− ∈ E has a well de ned source node but does not have a well de ned target node. 2 More speci cally, we have Above ϵ denotes a non-existing node. We denote the subset of E consisting of all of E's uncertain edges as E−.…”

“…We denote the subset of E consisting of all of E's uncertain edges as E−. ◇ Figure 2 includes two uncertain edges, e− (2) and e− (3) with di erent degrees. e uncertain edge e− (3) captures a form of uncertainty with mutual exclusion among the edges from i to d , e , or f .…”

“…Most existing works on graph uncertainty consider existence uncertainty, where a given edge exists probabilistically and the existence probabilities of the individual edges are assumed to be independent from each other [2,10,16,20,26,29]. In practice, however, this assumption does not always hold: we may be aware of the existence of an edge, but we may not know between which pairs of nodes the edge exists.…”

Enumeration of Maximal Cliques from an Uncertain Graph

“…In this work, we focus on uncertain graphs, where our knowledge is represented as a graph, and there is uncertainty in the presence of each edge in the graph. Uncertain graphs have been used extensively in modeling, for example, in communication networks [1], [2], [3], social networks [4], [5], [6], [7], [8], [9], protein interaction networks [10], [11], [12], and regulatory networks in biological systems [13].…”