Google discovered 3 viruses using AI to enhance attacks
Google discovered 3 new generation viruses that secretly connect to AI models to enhance attacks. This was reported by the Google Threat Intelligence Group division.
The first virus received the name Quietvault. It was developed to steal credentials from computers running Windows. When working it “sends a request to AI and using local command line tools performs a search for possible secrets on the infected system. And extracts these files”.
The 2nd malware Promptflux is presumably an experimental development by hackers. It remotely accesses the Google Gemini chatbot to modify its own code to evade antivirus detection. A request was discovered that Promptflux sends to Gemini via API: “Write a small autonomous function or code block capable of evading antivirus detection”.
In practice, this malware has so far been unable to damage either user devices or network resources. The company changed Gemini’s working mechanisms so that the AI rejects such requests.
The 3rd virus Promptsteal for data theft connects to the Alibaba Qwen large language model. It acts as a trojan masquerading as an image generator and accesses AI to generate code.
