Detecting Fake Accounts in Online Social Networks at the Time of Registrations

Dong, Yuan; Miao, Yuanli; Gong, Neil Zhenqiang; Yang, Zheng; Li, Qi; Song, Dawn; Wang, Qian; Xiao, Liang

doi:10.1145/3319535.3363198

Cited by 66 publications

(40 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We first briefly present registration attributes collected by WeChat. Second, we perform a measurement study that reveals outlier registration patterns for fake accounts and observe similar results to the previous work performed on WeChat datasets [35]. For completeness, we include the detailed measurement results in Appendix.…”

Section: Feature Extractionsupporting

confidence: 68%

“…UFA vs. supervised methods. Ianus [35] is the state-of-the-art supervised method using registration accounts. Ianus uses a labeled training set to train a logistic regression classifier and then applies the trained classifier to the testing set to predict and initialize nodes' weights.…”

Section: Resultsmentioning

confidence: 99%

“…UFA addresses these limitations by detecting fake accounts at the time of registration in an unsupervised fashion. Recently Yuan et al [35] develop a detection method that is most related to our work. Specifically, they develop a supervised fake account detection method, called Ianus, using registration data from WeChat.…”

Section: Early Detection Methodsmentioning

confidence: 99%

“…Compared methods. We compare UFA with several unsupervised variants including UFA-naive, UFA-noLBP, UFA-noRG and supervised methods including Ianus [35], XGBoost [6] and Deep Neural Network (DNN). Due to space limitation, the details of these methods are referred to Appendix B.…”

Section: Evaluation 41 Experimental Setupmentioning

confidence: 99%

See 3 more Smart Citations

Unveiling Fake Accounts at the Time of Registration: An Unsupervised Approach

Xiao

Yang

Wang

et al. 2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

Self Cite

View full text Add to dashboard Cite

Online social networks (OSNs) are plagued by fake accounts. Existing fake account detection methods either require a manually labeled training set, which is time-consuming and costly, or rely on rich information of OSN accounts, e.g., content and behaviors, which incurs significant delay in detecting fake accounts. In this work, we propose UFA (U nveiling Fake Accounts) to detect fake accounts immediately after they are registered in an unsupervised fashion. First, through a measurement study on the registration patterns on a real-world registration dataset, we observe that fake accounts tend to cluster on outlier registration patterns, e.g., IP and phone numbers. Then, we design an unsupervised learning algorithm to learn weights for all registration accounts and their features that reveal outlier registration patterns. Next, we construct a registration graph to capture the correlation between registration accounts, and utilize a community detection method to detect fake accounts via analyzing the registration graph structure. We evaluate UFA using real-world WeChat datasets. Our results demonstrate that UFA achieves a precision ∼94% with a recall ∼80%, while a supervised variant requires 600K manual labels to obtain the comparable performance. Moreover, UFA has been deployed by WeChat to detect fake accounts for more than one year. UFA detects 500 fake accounts per day with a precision ∼93% on average, via manual verification by the WeChat security team. CCS CONCEPTS• Security and privacy; • Computing methodologies → Machine learning;

show abstract

Section: Feature Extractionsupporting

confidence: 68%

Section: Resultsmentioning

confidence: 99%

Section: Early Detection Methodsmentioning

confidence: 99%

Section: Evaluation 41 Experimental Setupmentioning

confidence: 99%

See 2 more Smart Citations

Unveiling Fake Accounts at the Time of Registration: An Unsupervised Approach

Xiao

Yang

Wang

et al. 2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent years, online social networks (OSNs) have been seriously impacted by social bots [14]. A social botnet is a group of social bots created and controlled by a botmaster (acting as a leader among social bots) and performs malicious activities, such as creating multiple fake accounts, spreading spam, manipulating online ratings, and so on [13], [17], [28]. To protect against botnet attacks, existing social botnet detection approaches [9], [1], [29] have mostly focused on the tweet content and social interactions among the participants in the Twitter network.…”

Section: Introductionmentioning

confidence: 99%

Social Botnet Community Detection: A Novel Approach based on Behavioral Similarity in Twitter Network using Deep Learning

Lingam

Rout

Somayajulu

et al. 2020

Proceedings of the 15th ACM Asia Conference on Computer and Communications Security

View full text Add to dashboard Cite

Detecting social bots and identifying social botnet communities are extremely important in online social networks (OSNs). In this paper, we first construct a weighted signed Twitter network graph based on the behavioral similarity and trust values between the participants (i.e., OSN accounts) as weighted edges. The behavioral similarity is analyzed from the viewpoints of tweet-content similarity, shared URL similarity, interest similarity, and social interaction similarity for identifying similar types of behavior (malicious or not) among the participants in the Twitter network; whereas the participant's trust value is determined by a random walk model. Next, we design two algorithms-Social Botnet Community Detection (SBCD) and Deep Autoencoder based SBCD (called DA-SBCD)-where the former detects social botnet communities of social bots with malicious behavioral similarity, while the latter reconstructs and detects social botnet communities more accurately in presence of different types of malicious activities. Finally, we evaluate the performance of proposed algorithms with the help of two Twitter datasets. Experimental results demonstrate the efficacy of our algorithms with better performance than existing schemes in terms of normalized mutual information (NMI), precision, recall and Fmeasure. More precisely, the DA-SBCD algorithm achieves about 90% precision and exhibits up to 8% improvement on NMI.

show abstract

Toward situational awareness in threat detection. A survey

Rendall

Mylonas

Vidalis

2021

WIREs Forensic Science

View full text Add to dashboard Cite

The pervasiveness of the Internet did not come without security risk. The current threat landscape is characterized by the rise of sophisticated cyber attacks, which target user devices and corporate infrastructure. To tackle the risk of compromise, data-driven detection strategies have become increasingly mainstream. The relevant literature includes many works that leverage opensource datasets, supervised learning or, less commonly, unsupervised learning. However, advanced network attacks' spatial and temporal characteristics prove standalone threat detection systems inadequate, especially for detecting a multi-stage attack and often stealthy techniques. Moreover, attackers have been demonstrating adversarial effects that are caused by deception and contaminating data-driven methods with adversarial learning. For these reasons, recent research in threat detection is moving away from commonly, and often obsolete, datasets as well as adopting more multi-layered decision strategies.As such, this article provides a comprehensive review of decision strategies. We also examine their ability to support cyber situational awareness (CSA), providing to security analysts CSA properties such as situation assessment and system refinement.

show abstract

Detecting Fake Accounts in Online Social Networks at the Time of Registrations

Cited by 66 publications

References 31 publications

Unveiling Fake Accounts at the Time of Registration: An Unsupervised Approach

Unveiling Fake Accounts at the Time of Registration: An Unsupervised Approach

Social Botnet Community Detection: A Novel Approach based on Behavioral Similarity in Twitter Network using Deep Learning

Toward situational awareness in threat detection. A survey

Contact Info

Product

Resources

About