arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.01741cs.CRcs.AIcs.ARcs.LG
收藏

PVF:理解AI对SDC的脆弱性

PVF:Understanding AI Vulnerability Against SDCs

Meta Platforms, Inc(Meta平台)

Xun Jiao, Fred Lin, Harish D. Dixit, Joel Coburn, Sajin Nair, Abhinav Pandey, Han Wang, Venkat Ramesh, Jianyu Huang, Daniel Moore, Sriram Sankar

AI总结:

提出参数脆弱性因子(PVF)量化AI模型对参数损坏的脆弱性,应用于推荐、视觉和文本分类模型,并用于Meta AI芯片的错误管理设计。

摘要:

AI系统的可靠性是成功部署和广泛采用AI技术的基本关注点。不幸的是,AI硬件系统日益增长的复杂性和异构性使其更容易受到硬件故障的影响,例如静默数据损坏(SDC),这些故障可能破坏模型参数。当这种情况发生在AI推理/服务期间时,可能导致用户输出不正确或退化,最终影响AI服务的质量和可靠性。鉴于这一日益严重的威胁,解决关键问题至关重要:AI模型对参数损坏的脆弱性如何?模型的不同组件(如模块、层)对参数损坏的脆弱性如何变化?为了系统地解决这个问题,我们提出了一种新颖的量化指标——参数脆弱性因子(PVF),灵感来自计算机体系结构中的体系结构脆弱性因子(AVF),旨在标准化AI模型对参数损坏的脆弱性量化。我们将模型参数的PVF定义为该特定参数中的损坏导致错误输出的概率。在本文中,我们展示了将PVF应用于推理过程中的三种任务/模型——推荐(DLRM)、视觉分类(CNN)和文本分类(BERT)的几个用例,同时对DLRM进行了深入的脆弱性分析。PVF已成为在Meta内部AI芯片MTIA的生产化中用于做出关键错误管理设计决策的关键指标。

英文摘要:

Reliability of AI systems is a fundamental concern for the successful deployment and widespread adoption of AI technologies. Unfortunately, the escalating complexity and heterogeneity of AI hardware systems make them increasingly susceptible to hardware faults, e.g., silent data corruptions (SDC), that can potentially corrupt model parameters. When this occurs during AI inference/servicing, it can potentially lead to incorrect or degraded model output for users, ultimately affecting the quality and reliability of AI services. In light of the escalating threat, it is crucial to address key questions: How vulnerable are AI models to parameter corruptions, and how do different components (such as modules, layers) of the models exhibit varying vulnerabilities to parameter corruptions? To systematically address this question, we propose a novel quantitative metric, Parameter Vulnerability Factor (PVF), inspired by architectural vulnerability factor (AVF) in computer architecture community, aiming to standardize the quantification of AI model vulnerability against parameter corruptions. We define a model parameter's PVF as the probability that a corruption in that particular model parameter will result in an incorrect output. In this paper, we present several use cases on applying PVF to three types of tasks/models during inference -- recommendation (DLRM), vision classification (CNN), and text classification (BERT), while presenting an in-depth vulnerability analysis on DLRM. PVF has been a critical metric used for making key error management design decisions in productionizing Meta's in-house AI chip - MTIA.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑