NeurIPS · 2021 · Journal article

How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?

Dong, Xinhsuai, Tuan, Luu Anh, Min Lin, Shuicheng Yan, Hanwang Zhang

Published in: Neural Information Processing Systems
Date: 2021-12-22
Citations: 79
arXiv: 2112.11668 ↗

Cite

@article{xinhsuai2021should,
  title = {How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?},
  author = {Dong, Xinhsuai and Tuan, Luu Anh and Min Lin and Shuicheng Yan and Hanwang Zhang},
  year = {2021},
  journal = {Neural Information Processing Systems},
  eprint = {2112.11668},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2112.11668},
}