DAMAGeR: Deploying Automatic and Manual Approaches to GenAI Red-teaming

Manish Nagireddy, Michael Feffer, Ioana Baldini


Abstract
In this tutorial, we will review and apply current automatic and manual red-teaming techniques for GenAI models(including LLMs and multimodal models). In doing so, we aim to emphasize the importance of using a mixture of techniques and establishing a balance between automatic and manual approaches. Lastly, we aim to engage tutorial participants in live red-teaming activities to collaboratively learn impactful red-teaming strategies and share insights.
Anthology ID:
2025.naacl-tutorial.2
Volume:
Proceedings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 5: Tutorial Abstracts)
Month:
May
Year:
2025
Address:
Albuquerque, New Mexico
Editors:
Maria Lomeli, Swabha Swayamdipta, Rui Zhang
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10–14
Language:
URL:
https://preview.aclanthology.org/Author-page-Marten-During-lu/2025.naacl-tutorial.2/
DOI:
Bibkey:
Cite (ACL):
Manish Nagireddy, Michael Feffer, and Ioana Baldini. 2025. DAMAGeR: Deploying Automatic and Manual Approaches to GenAI Red-teaming. In Proceedings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 5: Tutorial Abstracts), pages 10–14, Albuquerque, New Mexico. Association for Computational Linguistics.
Cite (Informal):
DAMAGeR: Deploying Automatic and Manual Approaches to GenAI Red-teaming (Nagireddy et al., NAACL 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/Author-page-Marten-During-lu/2025.naacl-tutorial.2.pdf