MAD-MAX: Modular And Diverse Malicious Attack MiXtures for Automated LLM Red Teaming

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Schoepf, Stefan, Hameed, Muhammad Zaid, Rawat, Ambrish, Fraser, Kieran, Zizzo, Giulio, Cornacchia, Giandomenico, Purcell, Mark
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2503.06253