Boosting the Adversarial Transferability of Surrogate Model with Dark Knowledge. (arXiv:2206.08316v1 [cs.LG])

Web: http://arxiv.org/abs/2206.08316

Deep neural networks (DNNs) for image classification are known to be
vulnerable to adversarial examples. And, the adversarial examples have
transferability, which means an adversarial example for a DNN model can fool
another black-box model with a non-trivial probability. This gave birth of the
transfer-based adversarial attack where the adversarial examples generated by a
pretrained or known model (called surrogate model) are used to conduct
black-box attack. There are some work on how to generate the adversarial
examples from a …

arxiv boosting knowledge lg model