Adversarial Machine Learning in Latent Representations of Neural Networks

Distributed deep neural networks (DNNs) have been shown to reduce the computational burden of mobile devices and decrease the end-to-end inference latency in edge computing scenarios. While distributed DNNs have been studied, to the best of our knowledge the resilience of distributed DNNs to adversarial action still remains an open problem. In this paper, we fill the existing research gap by rigorously analyzing the robustness of distributed DNNs against adversarial action. We cast this problem in the context of information …

adversarial adversarial machine learning best of computational computing cs.ai cs.lg devices distributed edge edge computing inference knowledge latency machine machine learning mobile mobile devices networks neural networks reduce resilience