Top News

Google Gemini: Gemini AI of Google is a tool that can also create audio with video, prepare picture books for children and even plan your journey. But along with its bright aspects, there is a dangerous aspect of it, which a research team brought in a small but shocking demo.

You must have seen in films that someone controls the lights of the house from a distance or changes the temperature. But the researchers actually showed this feat and that too by hacking Gemini AI. He showed how changes can be made not only in the house by connecting AI with a smart device, but it can also cause serious damage.

According to WIRED report, the team hacked the Gemini Assistant on Android phone through a dangerous code Google calendar invoice. As soon as he sought information about the calendar from Gemini, the code was activated and started affecting all the devices of the house. In this way, a simple -looking calendar involved became the means of capturing the entire smart system of the house.

Although the researchers did not disclose the technical details, this demo was enough to show how devastating AI could prove to be in the wrong hands. Smart devices have already been victims of cyber attacks and now with the advent of LLM (large language model), this danger has increased manifold. Therefore, it is very important to ensure the safety of these models before the expansion of Smart Home AI.

This hacking demo was shared with Google and the company believes that control over AI can be dangerous through home appliances. Although Google says that this weakness has not yet been misused, it is working to overcome it. In the coming time, there are plans to bring Gemini to Smartwatch, Smart TV and even cars, which were announced in the main speech of I/O 2025. It is expected that Google and its security team will fix these weaknesses before cyber criminals taking advantage of them.