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.
AIvengo >
Reviews >
Google discovered 3 viruses using AI to enhance attacks
Почитать из последнего
UBTech will send Walker S2 robots to serve on China's border for $37 million
Chinese company UBTech won a contract for $37 million. And will send humanoid robots Walker S2 to serve on China's border with Vietnam. South China Morning Post reports that the robots will interact with tourists and staff, perform logistics operations, inspect cargo and patrol the area. And characteristically — they can independently change their battery.
AI chatbots generate content that exacerbates eating disorders
A joint study by Stanford University and the Center for Democracy and Technology showed a disturbing picture. Chatbots with artificial intelligence pose a serious risk to people with eating disorders. Scientists warn that neural networks hand out harmful advice about diets. They suggest ways to hide the disorder and generate "inspiring weight loss content" that worsens the problem.
OpenAGI released the Lux model that overtakes Google and OpenAI
Startup OpenAGI released the Lux model for computer control and claims this is a breakthrough. According to benchmarks, the model overtakes analogues from Google, OpenAI and Anthropic by a whole generation. Moreover, it works faster. About 1 second per step instead of 3 seconds for competitors. And 10 times cheaper in cost per processing 1 token.
