SybilInfer: Detecting Sybil Nodes using Social Networks

By George Danezis, Prateek Mittal. Network and Distributed System Security Symposium, 2009

442 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/653fbfbad9d565dd5e5e0d48b6bb32dd02e8f157

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Aiding the Detection of Fake Accounts in Large Scale Social Online Services (2012, methodology): “Although for analytical tractability, we assume that the non-Sybil region is fast mixing as in previous work [23, 53, 57], SybilRank’s effectiveness does not rely on the absolute value of the non-Sybil region’s mixing time.”
GANG: Detecting Fraudulent Users in Online Social Networks via Guilt-by-Association on Directed Graphs (2017, methodology): “Using undirected social graphs: Some guilt-by-association methods [5], [6], [7], [8], [9], [10], [11], [12], [13] assume symmetric relationships between nodes.”
SybilSCAR: Sybil detection in online social networks via local rule based propagation (2017, methodology): “Most structurebased methods [9], [10], [11], [12], [8], [13], [14], [15] can be grouped into two categories: Random Walk (RW)-based methods and Loop Belief Propagation (LBP)-based methods.”
Towards Detecting Anomalous User Behavior in Online Social Networks (2014, methodology): “In OSNs, where identities are associated with each other through hard-to-earn endorsement and friend edges, several graph-based Sybil detection schemes have been developed over the years [10, 52, 61, 66, 67].”
CrowdTarget: Target-based Detection of Crowdturfing in Online Social Networks (2015, background): “Second, graph-based methods [9, 10, 13, 30, 36, 37] detect malicious accounts by using the observation that malicious accounts usually have few connections with normal accounts.”
SybilBlind: Detecting Fake Users in Online Social Networks without Manual Labels (2018, methodology): “This assumption is required by all previous structurebased methods [39,38,8,26,7,36,6,14,30,33] except Íntegro [6].”
SybilFuse: Combining Local Attributes with Global Structure to Perform Robust Sybil Detection (2018, methodology): “For instance, random walk based approaches include SybilGuard [11], Sybil-Limit [12], SybilInfer [13], SybilRank [14], CIA [15], and SybilWalk [23].”
Trafficking Fraudulent Accounts: The Role of the Underground Market in Twitter Spam and Abuse (2013, background): “With no central operation of the underground market, we resort to investigating common haunts: advertisements via search engines, blackhat forums such as blackhat-world.com , and freelance labor pages including Fiverr and Freelancer [20, 21].”
The socialbot network: when bots socialize for fame and money (2011, background): “To defend against the Sybil attack, recent research propose to exploit the implicit social network among the nodes of a DHT in order to detect, and thereof limit, the number of Sybil nodes it may contain [15, 66, 67, 77, 78].”
Preserving Link Privacy in Social Network Based Systems (2012, methodology): “First, we propose an algorithm that perturbs the structure of a social graph in order to provide link privacy, at the cost of slight reduction in the utility of the social graph.”
Suspended accounts in retrospect: an analysis of twitter spam (2011, background): “They can do so by either forming relationships between their accounts to monitor tweet delivery (though this risks Sybil detection [4, 26]), or, alter-”
Exploiting Temporal Dynamics in Sybil Defenses (2015, methodology): “We then examine attacks based on churn in attack edges, including attacks on SybilInfer [8], SybilRank [7], and a powerful attack that undermines the effectiveness of the Persea Sybilresistant DHT [4].”
Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples (2019, background): “Sybil attacks [30, 132] can enable attackers to create a plethora of fake accounts and upload large amounts of OOD adversarial examples.”
Analyzing spammers' social networks for fun and profit: a case study of cyber criminal ecosystem on twitter (2012, methodology): “If criminal accounts mainly build inner social relationships within themselves, according to existing approaches such as Sybil Guard [37] and Sybil Infer [19] on detecting sybil nodes, criminal accounts can be easily detected.”
Structure-Based Sybil Detection in Social Networks via Local Rule-Based Propagation (2018, methodology): “RW-based methods [8], [9], [10], [11], [12], [13], [14], [15], [16] suffer from one or two major limitations: 1) they can only leverage either labeled benign users or labeled Sybils in the training dataset, but not both, which limits their detection accuracies; and”
The DARPA Twitter Bot Challenge (2016, unknown): “No team found existing Sybil detection methods [5,6] useful.”
Graph-based Security and Privacy Analytics via Collective Classification with Joint Weight Learning and Propagation (2018, background): “SybilInfer [9] Sybil Detection Undirected Negative N NDSS’09”
BotGrep: Finding P2P Bots with Structured Graph Analysis (2010, methodology): “We cluster P2P nodes by using the SybilInfer [21] framework.”