Adversarial Attack via Dual-Stage Network Erosion. (arXiv:2201.00097v1 [cs.CV])

Deep neural networks are vulnerable to adversarial examples, which can fool
deep models by adding subtle perturbations. Although existing attacks have
achieved promising results, it still leaves a long way to go for generating
transferable adversarial examples under the black-box setting. To this end,
this paper proposes to improve the transferability of adversarial examples, and
applies dual-stage feature-level perturbations to an existing model to
implicitly create a set of diverse models. Then these models are fused by the
longitudinal ensemble …

arxiv cv stage