LLMail-Inject: a Dataset from a Realistic Adaptive Prompt Injection Challenge

Indirect Prompt Injection attacks exploit the inherent limitation of Large Language Models LLMs to distinguish between instructions and data in their inputs. Despite numerous defense proposals, the systematic evaluation against adaptive adversaries remains limited, even when successful attacks ca...

Announcing the winners of the Adaptive Prompt Injection Challenge (LLMail-Inject)

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...

Announcing the Adaptive Prompt Injection Challenge (LLMail-Inject)

We are excited to introduce LLMail-Inject, a new challenge focused on evaluating state-of-the-art prompt injection defenses in a realistic simulated LLM-integrated email client. In this challenge, participants assume the role of an attacker who sends an email to a user. The user then queries the...