As part of its study, Microsoft researchers tested the Skeleton Key technique on a variety of leading AI models including Meta’s Llama3-70b-instruct, Google’s Gemini Pro, OpenAI’s GPT-3.5 ...

News. Microsoft Finds Multiple AI Models Susceptible to 'Skeleton Key' Attacks. By Gladys Rama; 07/02/2024; Popular AI models like OpenAI's GPT and Google's Gemini are liable to forget their built ...