Check out this insightful article on The Readable about an innovative AI model, DarkBERT, developed by Korean researchers from S2W and KAIST.

DarkBERT is designed to detect cybercrimes on the dark web by understanding the specific language used by criminals. Built on Google's BERT model, DarkBERT boasts a 90% accuracy rate in classifying illegal activities, significantly enhancing cyber threat intelligence.

"DarkBERT is expected to accelerate cybercrime investigations as well as contribute to the evolution of cyber threat intelligence (CTI) services."
— The Readable, Korean security researchers introduced new AI. And it is sweeping the globe

👉 For more details, read the full article on The Readable