New reports uncover jailbreaks, unsafe code and data theft risks in leading AI systems

Various generative artificial intelligence (GenAI) services have been found vulnerable to two types of jailbreak attacks that make it possible to produce illicit or dangerous content.

The first of the two techniques, codenamed Inception, instructs an AI tool to imagine a fictitious scenario, which can then be adapted into a second scenario within the first one where there exists no safety guardrails.

“Continued prompting to the AI within the second scenarios context can result in bypass of safety guardrails and allow the generation of malicious content,” the CERT Coordination Center (CERT/CC) said in an advisory released last week.

Read more at The Hacker News