Ignore This Title and HackAPrompt: Exposing Systemic Weaknesses of LLMs through a Global Scale Prompt Hacking Competition

Sander Schulhoff, Jeremy Pinto, Anaum Khan, Louis-Francois Bouchard, Chenglei Si, Svetlina Anati, Valen Tagliabue, Anson Liu Kost, Christopher Carnahan, Jordan Boyd-Graber

Abstract

Presents results from a global prompt hacking competition with 600K+ adversarial prompts, revealing systemic LLM vulnerabilities across multiple models and defense strategies.

Categories

Tags

Framework Mappings

Cite This Resource

@article{llmsec202300002,
  title = {Ignore This Title and HackAPrompt: Exposing Systemic Weaknesses of LLMs through a Global Scale Prompt Hacking Competition},
  author = {Sander Schulhoff and Jeremy Pinto and Anaum Khan and Louis-Francois Bouchard and Chenglei Si and Svetlina Anati and Valen Tagliabue and Anson Liu Kost and Christopher Carnahan and Jordan Boyd-Graber},
  year = {2023},
  journal = {EMNLP 2023},
  url = {https://arxiv.org/abs/2311.16119},
}