Fake accounts¶
Fake accounts (also called fake profiles, inauthentic accounts, or fraudulent accounts) are user profiles on social media platforms that misrepresent their identity or purpose. Common motivations include gaining influence, phishing, scamming, spreading misinformation, manipulating public opinion, and evading content moderation. The prevalence of fake accounts undermines platform integrity, harms legitimate users, and enables at-scale deception.
LinkedIn, Facebook, Twitter, and Instagram all struggle with fake account proliferation. LinkedIn's professional focus makes fake accounts particularly damaging: they enable credential fraud, recruitment scams, and access to sensitive professional networks. Detection is challenging because platforms cannot access ground truth and must infer authenticity from textual profiles, behavioral patterns, and network topology.
Key papers¶
- The Looming Threat of Fake and LLM-generated LinkedIn Profiles: Challenges and Opportunities for Detection and Prevention — Dataset of 3600 LinkedIn profiles (legitimate, human-created fake, ChatGPT-generated) and SSTE method for detection; first detector to discriminate LLM-generated from human-created fakes.
- [[2011-kontaxis-detecting-profile-cloning]] — Graph-based detection of cloned profiles on OSNs using user-specific identifying information and similarity scoring.
- [[2015-prieto-detecting-spammers-spam-nets]] — Feature selection and SVM methods for identifying spammers and spam networks on LinkedIn.
- [[2020-xiao-detecting-clusters-fake-accounts]] — Clustering approach identifying fake account patterns via raw account parameters and numerical feature distributions.
Related topics¶
- Fake news detection methods — computational approaches for detecting fake accounts and accounts
- Social Network Security — security and privacy in online social networks
- Content authentication — methods for verifying authenticity of user profiles and content
- Large Language Models — generation of fake profiles using LLMs