Towards Detecting Anomalous User Behavior in Online Social Networks

299 citations recorded by the source corpus.

How researchers see this paper

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

Large-Scale Unusual Time Series Detection (2015, methodology): “Our approach achieves a detection accuracy of over 80% (compared to 42% for baseline methods) and requires less than 0.5 seconds to process 1000 time series which is at least 3x faster than baseline algorithms.”
Finding and Characterizing Information Warfare Campaigns (2020, methodology): “The unsupervised machine learning models used include hierarchical [151], partitional [103], PCA-based [242], Stream-based [172], and correlated pairwise similarity [60].”
CrowdTarget: Target-based Detection of Crowdturfing in Online Social Networks (2015, background): “However, recent studies [29, 32] show that applying the techniques to detect crowdturﬁng accounts is vulnerable to simple evasion techniques, such as performing malicious tasks while doing normal behaviors.”
Fake Co-visitation Injection Attacks to Recommender Systems (2017, background): “[31]) of visits and co-visits, the service provider could detect certain fake covisitations and mitigate our attacks.”
REV2: Fraudulent User Prediction in Rating Platforms (2018, background): “For instance, rapid or regular rating behavior is typical of fraudulent entities like fake accounts, sybils and bots [7, 16, 30, 31].”