A new study has shown that AI chatbots can be easily hacked and used to obtain sensitive information about users. As scientists have discovered, hackers can use a procedure called “indirect rapid injection” (indirect rapid injection). It allows you to sneak malicious components into the system.

For example, an attacker inserts an invisible font into a request on a web page to be used by a chatbot to answer a user’s question. Thus, the researchers forced the Bing chatbot to obtain the user’s personal financial data. The program managed to “spoof” an unsuspecting user’s email IDs and financial information.

Source: Ferra

Previous articleGoodbye AirPods Max: These Sony headphones have 45 hours of battery life and adaptive noise canceling
Next article“Yandex” allowed employees to work from abroad
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.


Please enter your comment!
Please enter your name here