On the Evaluation of User Privacy in Deep Neural Networks using Timing Side Channel

arXiv:2208.01113v3 Announce Type: replace
Abstract: Recent Deep Learning (DL) advancements in solving complex real-world tasks have led to its widespread adoption in practical applications. However, this opportunity comes with significant underlying risks, as many of these models rely on privacy-sensitive data for training in a variety of applications, making them an overly-exposed threat surface for privacy violations. Furthermore, the widespread use of cloud-based Machine-Learning-as-a-Service (MLaaS) for its robust infrastructure support has broadened the threat surface to include a variety of …

adoption applications arxiv channel cs.cr cs.lg data deep learning evaluation led networks neural networks opportunity privacy real risks sensitive sensitive data training user privacy world