Workshop on Adversarial testing and Red-Teaming for generative AI (2023) - ACL Anthology

This page is part of a temporary preview of a proposed change that may be incomplete or contain mistakes. It is not official and will be removed when the change is merged or abandoned.

Workshop on Adversarial testing and Red-Teaming for generative AI (2023)

Venues:: artofsafety | WS

Volumes

Proceedings of the ART of Safety: Workshop on Adversarial testing and Red-Teaming for generative AI 7 papers

bib (full) Proceedings of the ART of Safety: Workshop on Adversarial testing and Red-Teaming for generative AI

Proceedings of the ART of Safety: Workshop on Adversarial testing and Red-Teaming for generative AI
Alicia Parrish

Red Teaming for Large Language Models At Scale: Tackling Hallucinations on Mathematics Tasks
Aleksander Buszydlik | Karol Dobiczek | Michał Teodor Okoń | Konrad Skublicki | Philip Lippmann | Jie Yang

Student-Teacher Prompting for Red Teaming to Improve Guardrails
Rodrigo Revilla Llaca | Victoria Leskoschek | Vitor Costa Paiva | Cătălin Lupău | Philip Lippmann | Jie Yang

Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge
Manuel Brack | Patrick Schramowski | Kristian Kersting

Measuring Adversarial Datasets
Yuanchen Bai | Raoyi Huang | Vijay Viswanathan | Tzu-Sheng Kuo | Tongshuang Wu

Discovering Safety Issues in Text-to-Image Models: Insights from Adversarial Nibbler Challenge
Gauri Sharma

Uncovering Bias in AI-Generated Images
Kimberley Baxter