Microsoft recently discovered a new type of generative AI jailbreak method called Skeleton Key that could impact the implementations of some large and small language models. This new method has the potential to subvert either the built-in model safety or platform safety systems and produce any content.
Microsoft security researchers, in partnership with other security experts, continue to proactively explore and discover new types of AI model and system vulnerabilities. In this post we are providing information about AI jailbreaks, a family of vulnerabilities that can occur when the defenses implemented to protect AI from producing harmful content fails.
Read about some of the key issues surrounding AI harms and vulnerabilities, and the steps Microsoft is taking to address the risk.
Microsoft, in collaboration with OpenAI, is publishing research on emerging threats in the age of AI, focusing on identified activity associated with known threat actors Forest Blizzard, Emerald Sleet, Crimson Sandstorm, and others. The observed activity includes prompt-injections, attempted misuse of large language models (LLM), and fraud.