Skip to content
April 2025 Page 5

April 2025

New Reports Uncover Jailbreaks, Unsafe Code, and Data Theft Risks in Leading AI Systems

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…