Resisting Deep Learning Models Against Adversarial Attack Transferability via Feature Randomization. (arXiv:2209.04930v1 [cs.CR])

In the past decades, the rise of artificial intelligence has given us the
capabilities to solve the most challenging problems in our day-to-day lives,
such as cancer prediction and autonomous navigation. However, these
applications might not be reliable if not secured against adversarial attacks.
In addition, recent works demonstrated that some adversarial examples are
transferable across different models. Therefore, it is crucial to avoid such
transferability via robust models that resist adversarial manipulations. In
this paper, we propose a feature …

arxiv deep learning feature randomization