Russian developers, with the support of the National Technology Initiative, have created an artificial intelligence tool that allows them to detect potentially malicious content in open and closed Telegram communities and chats, Izvestia reports.
Author:
https://rb.ru/author/kossakovskaya-anastasiya/
Subscribe to RB.RU on Telegram
The AI module, called Apparatus Sapiens, was developed back in 2023, but it was the update carried out in 2025 that made it possible to relate the malicious content found to its author.
“It allows you to analyze the content published on social networks and find signs of a crime. In the next stage, the author of the destructive and dangerous content is anonymized. The program works thousands of times faster than Telegram analysts,” Igor Bederov, creator of the software and director of the T.Hunter research department, told Izvestia.
Bederov added that the development is especially relevant in the context of a series of arson attacks on ATMs, police stations and military registration and enlistment offices that occurred before the New Year, which law enforcement agencies attributed to fraudsters from “hostile” countries.
According to Bederov, the AI module will identify malicious and attacking content using “dangerous” words, such as explosion or arson, but the key role will be played by the “color” of the message, which indicates its real danger. The module is also capable of downloading all the author’s public messages, analyzing his connections with other users and determining his region of residence.
“With the deanonymizer you can find data on 58 million Telegram users linked to phone numbers. The system also monitors 22 million chats, which include both public and private communities, access to which requires clicking on a link and agreeing with the administrator,” Bederov shared.
The information collected by the module is transmitted to law enforcement agencies, as required by existing cooperation agreements. The competent authorities will then decide on response measures, Bederov concluded.
Since tools like Apparatus Sapiens can pose certain risks, access to them should be strictly regulated and provided only to “verified organizations and individuals working within the law,” said Zhanna Meksheneva, head of the Faculty’s applied mathematics department. of Synergy Information Technologies. University, he told Izvestia.
Author:
Anastasia Kossakovskaya
Source: RB
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
