Hackers Hijacked Google’s Gemini AI With a Poisoned Calendar Invite to Take Over a Smart Home

According to the news article, security researchers have discovered a way to hack Google's Gemini AI system through a poisoned calendar invite. This allowed the hackers to gain control over a smart home, enabling them to turn off lights, open smart shutters, and cause other real-world disruptions. The incident is believed to be the first of its kind, demonstrating the potential vulnerabilities of AI systems and the ability of hackers to exploit them for malicious purposes. The researchers were able to manipulate the Gemini AI system by sending a calendar invite containing malicious code, which the system then executed, granting the hackers control over the connected smart home devices. This discovery highlights the importance of robust security measures and the need for AI developers to prioritize the security and resilience of their systems, particularly as they become more integrated into our daily lives and homes.