Google has confirmed it is deploying red team hacking bots to protect from ongoing Gemini AI prompt attacks—here’s what you need to know.

Multiple state-sponsored groups are experimenting with the AI-powered Gemini assistant from Google to increase productivity and to conduct research on potential infrastructure for attacks or for reconnaissance on targets.

Google announced Thursday that the Gemini app is getting its Gemini 2.0 Flash AI model. The upgraded model “delivers fast responses and stronger performance across a number of key benchmarks, providing everyday help with tasks like brainstorming,

Hacking units from Iran abused Gemini the most, but North Korean and Chinese groups also tried their luck. None made any 'breakthroughs' and mostly used Gemini for mundane tasks.

State-backed hackers from Iran, North Korea, China, and Russia tried to exploit Google's Gemini AI for malicious purposes, from phishing to malware creation.

Google's own cybersecurity teams found evidence of nation-state hackers using Gemini to help with some aspects of cyberattacks.

In recent months, a troubling discovery has been made about how North Korean hackers are using advanced AI tools to carry out cybercrimes and espionage. According to a report by Google, the North Korean government-backed cybercriminals have been using a powerful AI system called Google Gemini to enhance their hacking operations.

Analysis showed hackers are already leveraging the power of open AI systems for research, troubleshooting code, and manipulating content.