面向人类监督的软件掺杂分析
Software Doping Analysis for Human Oversight
AI总结:
本文提出一种结合形式化软件掺杂分析与概率证伪的黑盒分析框架,用于识别高风险决策系统和排放系统中的不公平与歧视性行为,以支持欧盟AI法案所要求的人类监督。
摘要:
本文介绍了一个旨在帮助减轻软件可能带来的社会风险的框架。具体而言,这涵盖了软件掺杂的各个方面,以及高风险决策系统中的不公平和歧视问题。软件掺杂一词指的是软件中包含的、违背用户利益的秘密添加的功能。软件掺杂的一个突出例子是柴油排放丑闻曝光时,在全球数百万辆汽车中发现的被篡改的排放清洁系统。本文的第一部分将软件掺杂分析的形式化基础与既有的概率证伪技术相结合,得出一种用于识别软件不良效应的黑盒分析技术。我们将该技术应用于柴油车的排放清洁系统,也应用于可能以不公平或歧视方式评估人类的高风险系统。我们展示了我们的方法如何能够辅助人机协同中的人类做出更明智、更负责任的决策。这是为了促进有效的人类监督,这将是欧盟即将出台的《人工智能法案》所强制执行的一项核心要求。我们以法律、哲学和心理学的视角,对此类系统可能引发的问题进行了补充性探讨,以完善我们的技术贡献。
英文摘要:
This article introduces a framework that is meant to assist in mitigating societal risks that software can pose. Concretely, this encompasses facets of software doping as well as unfairness and discrimination in high-risk decision-making systems. The term software doping refers to software that contains surreptitiously added functionality that is against the interest of the user. A prominent example of software doping are the tampered emission cleaning systems that were found in millions of cars around the world when the diesel emissions scandal surfaced. The first part of this article combines the formal foundations of software doping analysis with established probabilistic falsification techniques to arrive at a black-box analysis technique for identifying undesired effects of software. We apply this technique to emission cleaning systems in diesel cars but also to high-risk systems that evaluate humans in a possibly unfair or discriminating way. We demonstrate how our approach can assist humans-in-the-loop to make better informed and more responsible decisions. This is to promote effective human oversight, which will be a central requirement enforced by the European Union's upcoming AI Act. We complement our technical contribution with a juridically, philosophically, and psychologically informed perspective on the potential problems caused by such 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。