HIGHLIGHTS
- who: Dejian Guan and collaborators from the College of Computer, National University of Defense Technology, Changsha, China have published the article: Stylized Pairing for Robust Adversarial Defense, in the Journal: (JOURNAL)
- what: The authors propose an adversarial defense method independent of adversarial perturbations which utilizes a stylized pairing technique to encourage logits for a pair of images and the corresponding stylized image to be similar. On the one hand, there are approaches aiming to generate robust models against adversarial examples by introducing robust architectures or robust parameters. The authors propose an evaluation method to measure . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.