Read more https://thehackernews.com/2025/04/new-reports-uncover-jailbreaks-unsafe.html
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
Pensée du jour :
Ce que l'homme a fait ,
l'homme peut le défaire.
"No secure path in the world"
