Vulnerable GPU Memory Management: Towards Recovering Raw Data from GPU

Authors: Zhe Zhou (Chinese University of Hong Kong), Wenrui Diao (Chinese University of Hong Kong), Xiangyu Liu (Chinese University of Hong Kong), Zhou Li (ACM Member), Kehuan Zhang (Chinese University of Hong Kong), Rui Liu (Chinese University of Hong Kong)

Volume: 2017
Issue: 2
Pages: 57–73
DOI: https://doi.org/10.1515/popets-2017-0016

Download PDF

Abstract: According to previous reports, information could be leaked from GPU memory; however, the security implications of such a threat were mostly overlooked, because only limited information could be indirectly extracted through side-channel attacks. In this paper, we propose a novel algorithm for recovering raw data directly from the GPU memory residues of many popular applications such as Google Chrome and Adobe PDF reader. Our algorithm enables harvesting highly sensitive information including credit card numbers and email contents from GPU memory residues. Evaluation results also indicate that nearly all GPU-accelerated applications are vulnerable to such attacks, and adversaries can launch attacks without requiring any special privileges both on traditional multi-user operating systems, and emerging cloud computing scenarios.

Keywords: GPU, Memory Management

Copyright in PoPETs articles are held by their authors. This article is published under a Creative Commons Attribution-NonCommercial-NoDerivs license.