伦理困境下群体引导的隐私保护AI决策
Privacy-preserving Crowd-guided AI Decision-making in Ethical Dilemmas
摘要：
随着人工智能（AI）的快速发展，围绕AI的伦理问题日益受到关注。特别是，自动驾驶汽车在事故场景中可能面临道德困境，例如保持路线导致伤害行人或转向导致伤害乘客。为了研究这种道德困境，最近的研究采用了偏好聚合，其中每个选民表达她/他的偏好超过可能的道德困境的情况下的决定，和一个集中的系统聚合这些偏好，以获得获胜的决定。虽然这是一种构建道德AI系统的有用方法，但这种方法可能会侵犯选民的隐私，因为道德偏好是敏感信息，并且它们的披露可能会被恶意方利用。在本文中，我们报告了一种在道德困境中保护隐私的人群引导人工智能决策方法。我们采用差分隐私的概念来量化隐私，并考虑四个粒度的隐私保护，考虑投票/记录级隐私保护和集中/分布式扰动，导致四种方法VLCP，RLCP，VLDP，和RLDP。此外，我们提出了不同的算法来实现这些隐私保护粒度，同时保留了学习的道德偏好模型的准确性。具体地说，VLCP和RLCP的实现与数据聚合器设置一个通用的隐私参数和扰动的平均道德偏好，以保护选民的数据的隐私。VLDP和RLDP是以这样一种方式实现的，即每个选民都用个性化的隐私参数来扰乱她/他的本地道德偏好。在人工数据和真实数据上的大量实验表明，该方法可以在保护个人投票者隐私的同时实现高精度的偏好聚合。
英文摘要：
With the rapid development of artificial intelligence (AI), ethical issues surrounding AI have attracted increasing attention. In particular, autonomous vehicles may face moral dilemmas in accident scenarios, such as staying the course resulting in hurting pedestrians or swerving leading to hurting passengers. To investigate such ethical dilemmas, recent studies have adopted preference aggregation, in which each voter expresses her/his preferences over decisions for the possible ethical dilemma scenarios, and a centralized system aggregates these preferences to obtain the winning decision. Although a useful methodology for building ethical AI systems, such an approach can potentially violate the privacy of voters since moral preferences are sensitive information and their disclosure can be exploited by malicious parties. In this paper, we report a first-of-its-kind privacy-preserving crowd-guided AI decision-making approach in ethical dilemmas. We adopt the notion of differential privacy to quantify privacy and consider four granularities of privacy protection by taking voter-/record-level privacy protection and centralized/distributed perturbation into account, resulting in four approaches VLCP, RLCP, VLDP, and RLDP. Moreover, we propose different algorithms to achieve these privacy protection granularities, while retaining the accuracy of the learned moral preference model. Specifically, VLCP and RLCP are implemented with the data aggregator setting a universal privacy parameter and perturbing the averaged moral preference to protect the privacy of voters' data. VLDP and RLDP are implemented in such a way that each voter perturbs her/his local moral preference with a personalized privacy parameter. Extensive experiments on both synthetic and real data demonstrate that the proposed approach can achieve high accuracy of preference aggregation while protecting individual voter's privacy.
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。
