This video shares a novel method by Meta that uses another LLM, called the AdvPrompter, to generate human-readable adversarial prompts in seconds, ∼ 800× faster than existing optimization-based approaches. We train the AdvPrompter using a novel algorithm that does not require access to the
gradients of the TargetLLM.

▶ Become a Patron 🔥 -   / fahdmirza  

#advprompter #advpromptertrain #targetllm

PLEASE FOLLOW ME:
▶ LinkedIn:   / fahdmirza  
▶ YouTube:    / @fahdmirza  
▶ Blog: https://www.fahdmirza.com

RELATED VIDEOS:

▶ Paper https://arxiv.org/pdf/2404.16873

All rights reserved © 2021 Fahd Mirza