arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.00896cs.CRcs.AIcs.LG
收藏

基于云的AI服务的隐私与安全影响:一项综述

Privacy and Security Implications of Cloud-Based AI Services : A Survey

Nanyang Technological University(南洋理工大学)

Alka Luqman, Riya Mahesh, Anupam Chattopadhyay

AI总结:

该综述针对云AI服务中机器学习模型风险应对的空白,调研AIaaS领域风险并提出分类体系,梳理各方风险与防御措施,为构建隐私安全且稳健的AI系统奠定基础。

摘要:

本文详细阐述了当前云生态系统中的隐私与安全状况,并指出在应对机器学习模型带来的风险方面存在空白。随着机器学习算法持续演进并在多个不同领域得到应用,对隐私与安全风险进行分类和量化的需求变得愈发关键。随着人工智能即服务(AI-as-a-Service,AIaaS)这一新兴趋势的出现,机器学习训练得到的AI模型(或称ML模型)由模型提供方部署在云端,供模型消费方使用。我们首先调研了AIaaS领域,记录了ML模型尤其是深度神经网络(Deep Neural Networks)带来的各类风险责任,随后提出了一种分类体系,通过全面考察ML模型的创建方与消费方面临的风险以及迄今已知的防御措施来填补这一空白。这种结构化方法将有助于ML模型提供方打造稳健的解决方案,同样,ML模型消费方也可借助它评估此类解决方案,并了解自身使用这类服务的影响。所提出的分类体系为隐私、安全且稳健的机器学习解决方案提供了基础,为构建更透明、更具韧性的AI系统铺平了道路。

英文摘要:

This paper details the privacy and security landscape in today's cloud ecosystem and identifies that there is a gap in addressing the risks introduced by machine learning models. As machine learning algorithms continue to evolve and find applications across diverse domains, the need to categorize and quantify privacy and security risks becomes increasingly critical. With the emerging trend of AI-as-a-Service (AIaaS), machine learned AI models (or ML models) are deployed on the cloud by model providers and used by model consumers. We first survey the AIaaS landscape to document the various kinds of liabilities that ML models, especially Deep Neural Networks pose and then introduce a taxonomy to bridge this gap by holistically examining the risks that creators and consumers of ML models are exposed to and their known defences till date. Such a structured approach will be beneficial for ML model providers to create robust solutions. Likewise, ML model consumers will find it valuable to evaluate such solutions and understand the implications of their engagement with such services. The proposed taxonomies provide a foundational basis for solutions in private, secure and robust ML, paving the way for more transparent and resilient AI systems.

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。

↑