Reposted by Georgios Panayiotou
🧪 New #CIKM paper: Adversarial Creation & Detection of AI-Generated Social Bot Content
We build evil AI twins impersonating social media users. A model trained to separate humans from their evil twins rocks at detecting AI bots in the wild!
Try it: botometer.org
Preprint: doi.org/10.48550/arX...
![Comic. [A person and a second person with a ponytail sitting at a table with a screen showing a soccer game behind them.] PERSON 1: They could be in trouble. Over the last 36 years, they’ve gone 0 for 2 when they’ve scored in the 37th minute to lead 2-1 against a team whose country comes before theirs alphabetically. [caption] I wish sports commentators hadn’t discovered p-hacking.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:cz73r7iyiqn26upot4jtjdhk/bafkreia7nj3d2xiski77uifyleeowddz6c24e5tgcxrk4jy5j6o3i2wryu)
