Meta presents AdvPrompter Fast Adaptive Adversarial Prompting for LLMs.

Meta presents AdvPrompter.

Fast Adaptive Adversarial Prompting for LLMs https://huggingface.co/papers/2404.

While recently Large Language Models (LLMs) have achieved remarkable successes, they are vulnerable to certain jailbreaking attacks that lead to generation of inappropriate or harmful…

---

Join the discussion on this paper page.