Critical vulnerability detected in Apple Intelligence, not yet available

Artificial intelligence that American technology giant Apple will introduce to its users in a few months Apple Intelligence There was a notable development regarding this topic. A cybersecurity researcher has identified a significant vulnerability in this artificial intelligence. Artificial intelligence as a result of this vulnerability can be easily manipulated.

A cybersecurity expert named Evan Zhou has gained access to Apple Intelligence, which he runs on macOS 15.1. added a few lines of code. This code caused the AI ​​to ignore previous instructions. The research showed that Apple Intelligence can be easily manipulated. Because artificial intelligence, thanks to these few lines of code began to produce unpredictable responses.

Vulnerability can also be exploited for risky scenarios

Cybersecurity experts say a vulnerability has been discovered in Apple’s artificial intelligence They think it is crucial. Because artificial intelligence, which can be manipulated with a few rules, can be used for much riskier scenarios such as leaking user data. In the meantime; “rapid injectionThis attack technique, called “, is not specific to Apple Intelligence, but applies to all major language models as well. you risked let’s say.

Apple has not made any statement about the vulnerability in question. in the statement not foundHowever, the Apple Intelligence technology, which has not yet been officially released, already has security vulnerabilities. not on the agenda This fact also needs to be emphasized. We have readers who remember; In a news story we shared with you a while ago, we stated that Apple Intelligence cannot distinguish between emails sent for fraudulent purposes. we mentioned. Let’s see what issues we will talk about in the coming days…