Adversarial Nibbler
Data-centric AI Competition for Adversarial Examples for Text-to-Image Models
Adversarial Nibbler Video DataPerf.mp4! This challenge is coming soon !
Adversarial Nibbler is a data-centric AI competition that aims to construct a diverse set of insightful examples of long tail problems for text-to-image models. This way we can help identify blind spots in harmful image production (i.e., unknown unknowns).
This competition is a timely response to identify and mitigate safety concerns in a structured and systematic manner.
You can view a transcript of the video recording for this challenge here.
Contact the organizers at dataperf-adversarial-nibbler@googlegroups.com or join our slack channel at adversarial-nibbler.slack.com
Task Owners
Alicia Parrish (Google)
Lora Aroyo (Google)
Oana Inel (University of Zurich)
Charvi Rastogi (Carnegie Mellon University)
Jessica Quaye (Harvard University)
Hannah Rose Kirk (Oxford University)
Vijay Janapa Reddi (Harvard University)
Max Bartolo (UCL, Cohere)
Rafael Mosquera (ML Commons)
Juan Ciro (ML Commons)
D. Sculley (Kaggle)
Will Cukierski (Kaggle)
Addison Howard (Kaggle)
