Reproduce “Ephemeral Astroturfing Attacks: The Case of Fake Twitter Trends” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Tuğrulcan Elmas, Rebekah Overdorf, Ahmed Furkan Özkalay, Karl Aberer
Researchers from EPFL identified and analyzed 'ephemeral astroturfing,' a covert form of social media manipulation where attackers rapidly post and delete content to artificially inflate Twitter trends. This technique exploits a vulnerability in Twitter's trending algorithm, leading to over 19,000 fake trends and significantly impacting the authenticity of popular topics on the platform.
Key insights
- Ephemeral astroturfing exploits a Time-of-Check-Time-of-Use (TOCTOU) vulnerability in Twitter's trending algorithm, which considers tweets for popularity without checking if they are subsequently deleted.
- The attacks are operated as a 'service' model, with astrobot communities promoting diverse and often conflicting content (illicit ads, political propaganda, cult slogans) for commercial gain.
- A significant portion of accounts used in these attacks are compromised legitimate user accounts, whose owners are often unaware their accounts are being used to post and rapidly delete content.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.