Are Aligned Neural Networks Adversarially Aligned?

Nicholas Carlini, Milad Nasr, Christopher A. Choquette-Choo, Matthew Jagielski, Irena Gao, Anas Awadalla, Pang Wei Koh, Daphne Ippolito, Katherine Lee, Florian Tramer, Ludwig Schmidt

Abstract

Evaluates whether multimodal LLMs aligned to refuse harmful text requests also refuse harmful image-based requests, finding significant gaps.

Categories

Tags

Framework Mappings

Cite This Resource

@article{llmsec202500019,
  title = {Are Aligned Neural Networks Adversarially Aligned?},
  author = {Nicholas Carlini and Milad Nasr and Christopher A. Choquette-Choo and Matthew Jagielski and Irena Gao and Anas Awadalla and Pang Wei Koh and Daphne Ippolito and Katherine Lee and Florian Tramer and Ludwig Schmidt},
  year = {2024},
  journal = {NeurIPS 2023},
  url = {https://arxiv.org/abs/2306.15447},
}