arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.04884cs.CRcs.AI
收藏

机器学习安全风险管理框架

Risk Management Framework for Machine Learning Security

Silicon Austria Labs(奥地利硅谷实验室);Graz University of Technology(格拉茨工业大学);HP Labs(惠普实验室);HP-NTU Digital Manufacturing Corporate Lab(惠普-南洋理工大学数字制造企业实验室)

Jakub Breier, Adrian Baldwin, Helen Balinsky, Yang Liu

摘要:

针对机器学习模型的对抗攻击已经成为学术界和工业界高度研究的主题。这些攻击与传统的安全威胁一起,可能会危及依赖于机器学习模型使用的组织资产的机密性、完整性和可用性。虽然预测可能随着时间的推移而发展的新攻击类型并不容易,但可以评估与使用机器学习模型相关的风险,并设计有助于最大限度地降低这些风险的措施。在本文中,我们概述了一个新的框架,以指导依赖于机器学习模型的组织的风险管理过程。首先,我们在数据域、模型域和安全控制域中定义评估因子(EF)集。我们开发了一种方法,采取资产和任务的重要性,设置权重的EFs的贡献的机密性,完整性和可用性,并根据实施分数的EFs,它确定在组织的整体安全状态。根据这些信息,可以确定所实施的安全措施中的薄弱环节,并找出哪些措施可能完全缺失。我们相信我们的框架可以帮助解决与组织中使用机器学习模型相关的安全问题,并指导他们专注于保护其资产的适当安全措施。

英文摘要:

Adversarial attacks for machine learning models have become a highly studied topic both in academia and industry. These attacks, along with traditional security threats, can compromise confidentiality, integrity, and availability of organization's assets that are dependent on the usage of machine learning models. While it is not easy to predict the types of new attacks that might be developed over time, it is possible to evaluate the risks connected to using machine learning models and design measures that help in minimizing these risks. In this paper, we outline a novel framework to guide the risk management process for organizations reliant on machine learning models. First, we define sets of evaluation factors (EFs) in the data domain, model domain, and security controls domain. We develop a method that takes the asset and task importance, sets the weights of EFs' contribution to confidentiality, integrity, and availability, and based on implementation scores of EFs, it determines the overall security state in the organization. Based on this information, it is possible to identify weak links in the implemented security measures and find out which measures might be missing completely. We believe our framework can help in addressing the security issues related to usage of machine learning models in organizations and guide them in focusing on the adequate security measures to protect their assets.

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。

↑