We are excited to announce the winners of LLMail-Inject, our first Adaptive Prompt Injection Challenge! The challenge ran from December 2024 until February 2025 and was featured as one of the four official competitions of the 3rd IEEE Conference on Secure and Trustworthy Machine Learning (IEEE SaTML). The overall aims of this challenge were to advance the state-of-the-art defenses against indirect prompt injection attacks and to broaden awareness of these new techniques.
This article has been indexed from Microsoft Security Response Center