按年被提到
20132017 · 2 次2026
安全、隐私与密码学›侧信道与硬件攻击·arXiv:1305.7383 · cs.CR

CUDA Leaks: Information Leakage in GPU Architectures

Roberto Di Pietro, Flavio Lombardi, Antonio Villani · 2013
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2017-04-27 · 最近 2017-05-15
2不同的人
2活跃月份
2讨论串
84被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Graphics Processing Units (GPUs) are deployed on most present server, desktop, and even mobile platforms. Nowadays, a growing number of applications leverage the high parallelism offered by this architecture to speed-up general purpose computation. This phenomenon is called GPGPU computing (General Purpose GPU computing). The aim of this work is to discover and highlight security issues related to CUDA, the most widespread platform for GPGPU computing. In particular, we provide details and proofs-of-concept about a novel set of vulnerabilities CUDA architectures are subject to, that could be exploited to cause severe information leak. Following (detailed) intuitions rooted on sound engineering security, we performed several experiments targeting the last two generations of CUDA devices: Fermi and Kepler. We discovered that these two families do suffer from information leakage vulnerabilities. In particular, some vulnerabilities are shared between the two architectures, while others are idiosyncratic of the Kepler architecture. As a case study, we report the impact of one of these vulnerabilities on a GPU implementation of the AES encryption algorithm. We also suggest software patches and alternative approaches to tackle the presented vulnerabilities. To the best of our knowledge this is the first work showing that information leakage in CUDA is possible using just standard CUDA instructions. We expect our work to pave the way for further research in the field.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论paulmd · 2017-04

“There's two killers, compatibility and launch overhead. CUDA is the most commonly-used compute language but it's NVIDIA-only. OpenCL is "universal" (sort of) but - being a general-purpose framework for heterogeneous compute rather than a task-specific GPGPU language - it's much more complex and lacks the libraries/etc that are available in CUDA. NVIDIA's…”

Pushing a Trillion Row Database with GPU Acceleration原评论 ↗
评论inetknght · 2017-05

“Yup, I'd strongly consider something similar. But I'd have to seriously consider the security implications: giving Windows access to the graphics card could end up being more hassle than it's worth. GPUs' memory management isn't exactly security friendly. -> https://arxiv.org/pdf/1305.7383.pdf”

Don't tell people to turn off Windows Update原评论 ↗