New Virus Attack Using AI: How PromptLock Steals Data.

Experts at ESET Research Labs have discovered a unique piece of malware PromptLock, which for the first time in history uses artificial intelligence for attacks. According to the research, this ransomware uses immutable prompts sent to a local AI model. The intelligent model in turn generates Lua scripts in real-time to scan the file system, steal or encrypt data.

Features of PromptLock

According to inkorr.com: For its operation, PromptLock uses the open model gpt-oss-20b, released by OpenAI less than a month ago. This allows the malware to successfully operate on various operating systems, such as Windows, Linux, and macOS.

A New Era in Cybercrime

The PromptLock malware has become the first of its kind to choose artificial intelligence for attacks, using the gpt-oss-20b model. This could create new opportunities for cybercriminals to attack different operating systems.

This case demonstrates how technologies developed for innovation can be adapted by malicious actors for illegal activities. Given the increasing use of artificial intelligence in various fields, it is important to be cautious and protect personal information from potential attacks. Cybersecurity is becoming yet another critically important component of our digital lives.