Work

Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs Through a Global Prompt Hacking Competition

Year: 2023

Type: conference-paper

Abstract: Sander Schulhoff, Jeremy Pinto, Anaum Khan, Louis-François Bouchard, Chenglei Si, Svetlina Anati, Valen Tagliabue, Anson Kost, Christopher Carnahan, Jordan Boyd-Graber. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/2023.emnlp-main.302

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

Institutions: University of Maryland, College Park, Stanford University, Technical University of Sofia, University of Milan, New York University, University of Arizona

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W4389523893

FWCI: 18.08

Cites: 36

Cited by: 157

Related to: 10