⚠️ Severity: Low

Announcing the Adaptive Prompt Injection Challenge (LLMail-Inject)

🌍 Limbă / Language:
Traducere automată / Automatic translation
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 LLMail service with a question (e.

📌 Informații despre sursă

Sursă: Microsoft Security
Importat la: 12 October 2025, 08:46
Publicat: 6 December 2024

⚠️ Această știre a fost importată automat din surse oficiale. Pentru informații actualizate, vă rugăm să consultați direct site-ul sursei.

top
en_USEnglish
Simplifying IT
for a complex world.
Platform partnerships