On the Privacy Risks of Cell-Based NAS Architectures

Huang, Hai and Zhang, Zhikun and Shen, Yun and Backes, Michael and Li, Qi and Zhang, Yang
(2022) On the Privacy Risks of Cell-Based NAS Architectures.
In: CCS 2022.
Conference: CCS ACM Conference on Computer and Communications Security

[img]
Preview
Text
CCS22-NAS.pdf

Download (1MB) | Preview

Abstract

Existing studies on neural architecture search (NAS) mainly focus on efficiently and effectively searching for network architectures with better performance. Little progress has been made to systematically understand if the NAS-searched architectures are robust to privacy attacks while abundant work has already shown that human-designed architectures are prone to privacy attacks. In this paper, we fill this gap and systematically measure the privacy risks of NAS architectures. Leveraging the insights from our measurement study, we further explore the cell patterns of cell-based NAS architectures and evaluate how the cell patterns affect the privacy risks of NAS-searched architectures. Through extensive experiments, we shed light on how to design robust NAS architectures against privacy attacks, and also offer a general methodology to understand the hidden correlation between the NAS-searched architectures and other privacy risks.

Actions

Actions (login required)

View Item View Item