Chinese police used AI to monitor dark web content

Chinese police scientists have provided a rare glimpse into their methods for infiltrating and monitoring the dark web, leveraging artificial intelligence to decipher underground content. The dark web, known for its encrypted communications and anonymous routing, typically makes user activity difficult to trace, serving as a refuge for illicit activities and data trafficking.

While researchers globally have made strides in analyzing dark web content, most efforts have concentrated on English-language material. Little research has been published concerning Chinese-language content on the dark web. However, a research team from the Criminal Investigation Police University of China published a paper in May detailing a model specifically trained to translate and assess dark web content in Chinese.

The initial hurdle for the researchers was gaining access to dark websites to collect data. They encountered diverse login requirements across different platforms, and traditional web crawlers struggled with Captcha verification and the constantly evolving anti-scraping measures employed by these sites. To address these challenges, the team designed a specialized system capable of handling various tasks, including logging in, creating lists of content, and downloading images.