ChatGPT, Other Generative AI Apps Prone to Compromise, Manip

Researchers find artificial intelligence applications that use large language models could be compromised by attackers using natural language to dupe users.

Related Keywords

United States , Christoph Endres , Kai Greshake , Sequire Technology , Helmholtz Center , Saarland University , Samsung , Black Hat United States , Integrated Applications , Indirect Prompt , Black Hat , Information Security , Indirect Prompt Injection , ,