Evaluating the Robustness of Bayesian Neural Networks Against Different Types of Attacks

Published in CVPR 2021 Workshop on Adversarial Machine Learning in Real-World Computer Vision Systems, 2021 · arXiv

Evaluates how Bayesian neural networks hold up against different classes of adversarial attacks.

Recommended citation

@inproceedings{pang2021evaluating,
  title = {Evaluating the Robustness of Bayesian Neural Networks Against Different Types of Attacks},
  author = {Pang, Y. and Cheng, S. and Hu, J. and Liu, Y.},
  booktitle = {CVPR 2021 Workshop on Adversarial Machine Learning in Real-World Computer Vision Systems},
  year = {2021},
  eprint = {2106.09223},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2106.09223}
}