Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse
Harms in Text-to-Image Generation

v1v2v3 (latest)

Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation

14 February 2024

Hannah Rose Kirk

Rafael Mosquera

Vijay Janapa Reddi

Lora Aroyo

ArXiv (abs)PDF HTML

Papers citing "Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation"

1 / 1 papers shown

Title
A Systematic Review of Open Datasets Used in Text-to-Image (T2I) Gen AI Model Safety Rakeen Rouf Trupti Bavalatti Osama Ahmed Dhaval Potdar Faraz Jawed EGVM 133 2 0 23 Feb 2025