Lifeboat Foundation: Safeguarding Humanity

Toggle sitemap Toggle light / dark theme

Blog

Paper page — Red Teaming GPT-4V: Are GPT-4V Safe Against Uni/Multi-Modal Jailbreak Attacks?

Posted by Cecile G. Tamura in futurism

Apr 5
2024

Red Teaming GPT-4V

Are GPT-4V safe against uni/multi-modal jailbreak attacks?

Join the discussion on this paper page.