Using Single-Step Adversarial Training to Defend Iterative Adversarial Examples

Guanxiong Liu, Issa Khalil, Abdallah Khreishah. Using Single-Step Adversarial Training to Defend Iterative Adversarial Examples. In Anupam Joshi, Barbara Carminati, Rakesh M. Verma, editors, CODASPY '21: Eleventh ACM Conference on Data and Application Security and Privacy, Virtual Event, USA, April 26-28, 2021. pages 17-27, ACM, 2021. [doi]

@inproceedings{LiuKK21,
  title = {Using Single-Step Adversarial Training to Defend Iterative Adversarial Examples},
  author = {Guanxiong Liu and Issa Khalil and Abdallah Khreishah},
  year = {2021},
  doi = {10.1145/3422337.3447841},
  url = {https://doi.org/10.1145/3422337.3447841},
  researchr = {https://researchr.org/publication/LiuKK21},
  cites = {0},
  citedby = {0},
  pages = {17-27},
  booktitle = {CODASPY '21: Eleventh ACM Conference on Data and Application Security and Privacy, Virtual Event, USA, April 26-28, 2021},
  editor = {Anupam Joshi and Barbara Carminati and Rakesh M. Verma},
  publisher = {ACM},
  isbn = {978-1-4503-8143-7},
}