SybilRadar: A Graph-Structure Based Framework for Sybil Detection in On-line Social Networks

Abstract

Part 5: Social NetworksInternational audienceOnline Social Networks (OSN) are increasingly becoming victims of Sybil attacks. These attacks involve creation of multiple colluding fake accounts (called Sybils) with the goal of compromising the trust underpinnings of the OSN, in turn, leading to security and the privacy violations. Existing mechanisms to detect Sybils are based either on analyzing user attributes and activities, which are often incomplete or inaccurate or raise privacy concerns, or on analyzing the topological structures of the OSN. Two major assumptions that the latter category of works make, namely, that the OSN can be partitioned into a Sybil and a non-Sybil region and that the so-called “attack edges” between Sybil nodes and non-Sybil nodes are only a handful, often do not hold in real life scenarios. Consequently, when attackers engineer Sybils to behave like real user accounts, these mechanisms perform poorly. In this work, we propose SybilRadar, a robust Sybil detection framework based on graph-based structural properties of an OSN that does not rely on the traditional non-realistic assumptions that similar structure-based frameworks make. We run SybilRadar on both synthetic as well as real-world OSN data. Our results demonstrate that SybilRadar has very high detection rate even when the network is not fast mixing and the so-called “attack edges” between Sybils and non-Sybils are in the tens of thousands

Stopping the Cyberattack in the Early Stage: Assessing the Security Risks of Social Network Users

“…Then those similarity values are put as weights on the social graph to get actual attack edges. Finally, they use Supervised Random Walk to rank the nodes [12]. Lee [7].…”

“…Existing detection methods are mainly divided into two categories. The first category is the detection algorithms based on the relation graph of social networks [10][11][12]. Many kinds of relations exist in social networks, so researchers use relations in social networks to build a social graph.…”

An Analysis of Graph Properties for Detecting Sybil Nodes in Social Networks

“…Cao, et al proposed Sybil Rank [3], while Integro [16] and Sybil Radar [17] improved this method by applying machine learning. The researchers assumed that social networks have only a small number of victim nodes.…”

“…The mixing time of a social network containing only honest nodes tends to be faster than that of a social network containing Sybil nodes. Several researchers have used the mixing time to detect Sybil nodes [3,[8][9][10][11][12][13][14][15][16][17][18], but they did not sufficiently substantiate the underlying assumptions in their works. In this paper, we propose a process for measuring the mixing time in social networks using second largest eigenvalue modulus (SLEM).…”

“…However, there has been no research that analyzed the properties of individual nodes to distinguish between honest and Sybil nodes. This paper proposes a way to investigate the properties of all nodes in a social network so that Sybil nodes can be differentiated from honest nodes [10,[16][17][18][19][20][21][22].…”