SecurityENFreitag, 28. November 2025

Prompt Injection Through Poetry

Schneier on Security

External Source

Summary

In a new paper, “Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models,” researchers found that turning LLM prompts into poetry resulted in jailbreaking the models...

External Article

This article is from Schneier on Security and is hosted there. We only link to external sources and do not host any content on our servers.