2024-06-12 15:17:12.AIbase.9.6k
Researchers Find GPT-4o Easier to Jailbreak with Overall Security Inferior to GPT-4V
A joint research team from Beihang University and Nanyang Technological University conducted extensive security tests on the GPT-4o model. Through thousands of API queries, researchers evaluated the security of text, image, and audio modalities of GPT-4o. The study found that while GPT-4o showed improvements in security against text jailbreak attacks, the newly introduced audio modality presented new attack surfaces, and its overall multimodal security was not as strong as the previous generation model GPT-4V.
