论机器学习的安全性:网络物理系统、决策科学和数据产品
On the Safety of Machine Learning: Cyber-Physical Systems, Decision Sciences, and Data Products
摘要:
机器学习算法越来越多地影响我们的决策,并在我们日常生活的各个方面与我们互动。因此,正如我们考虑发电厂、高速公路和其他各种工程社会技术系统的安全性一样,我们也必须考虑涉及机器学习的系统的安全性。因此,安全的定义尚未在机器学习上下文中正式化。在本文中,我们通过从风险、认知不确定性和不想要的结果所造成的伤害的角度来定义机器学习安全性。然后,我们使用这个定义来检查网络物理系统,决策科学和数据产品中各种应用的安全性。我们发现,现代统计机器学习的基本原则,经验风险最小化,并不总是一个足够的目标。最后,我们讨论了四个不同类别的策略,实现工程安全,包括固有的安全设计,安全储备,安全故障,程序保障措施可以映射到一个机器学习上下文。然后,我们讨论了可以在每个类别中采用的示例技术,例如考虑预测模型的可解释性和因果关系,超出预期预测精度的目标函数,标记困难或罕见示例的人工参与,以及软件和开放数据的用户体验设计。
英文摘要:
Machine learning algorithms increasingly influence our decisions and interact with us in all parts of our daily lives. Therefore, just as we consider the safety of power plants, highways, and a variety of other engineered socio-technical systems, we must also take into account the safety of systems involving machine learning. Heretofore, the definition of safety has not been formalized in a machine learning context. In this paper, we do so by defining machine learning safety in terms of risk, epistemic uncertainty, and the harm incurred by unwanted outcomes. We then use this definition to examine safety in all sorts of applications in cyber-physical systems, decision sciences, and data products. We find that the foundational principle of modern statistical machine learning, empirical risk minimization, is not always a sufficient objective. Finally, we discuss how four different categories of strategies for achieving safety in engineering, including inherently safe design, safety reserves, safe fail, and procedural safeguards can be mapped to a machine learning context. We then discuss example techniques that can be adopted in each category, such as considering interpretability and causality of predictive models, objective functions beyond expected prediction accuracy, human involvement for labeling difficult or rare examples, and user experience design of software and open data.
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。