arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.07334cs.HCcs.CRcs.CYcs.LG
收藏

Tournesol:寻求一个大型,安全和值得信赖的可靠人类判断数据库

Tournesol: A quest for a large, secure and trustworthy database of reliable human judgments

EPFL(洛桑联邦理工学院);Tournesol Association(Tournesol协会);University of Tours(图尔大学);CNAM(法国国立工艺学院);CNRS(法国国家科学研究中心);UM6P(穆罕默德六世理工大学);INSA Lyon(里昂国立应用科学学院);École Polytechnique(巴黎综合理工学院)
Lê-Nguyên Hoang, Louis Faucon, Aidan Jungo, Sergei Volodin, Dalia Papuc, Orfeas Liossatos, Ben Crulis, Mariame Tighanimine, Isabela Constantin, Anastasiia Kuche… 展开作者

Lê-Nguyên Hoang, Louis Faucon, Aidan Jungo, Sergei Volodin, Dalia Papuc, Orfeas Liossatos, Ben Crulis, Mariame Tighanimine, Isabela Constantin, Anastasiia Kucherenko, Alexandre Maurer, Felix Grimberg, Vlad Nitu, Chris Vossen, Sébastien Rouault, El-Mahdi El-Mhamdi

摘要:

当今的大规模算法已经变得非常有影响力,因为它们推荐和审核数十亿人每天接触的内容。他们是我们社会信息饮食的事实上的监管者,从塑造公共卫生观点到组织社会运动团体。这引起了严重的关切,但也带来了促进高质量信息的巨大机会。解决这些问题并抓住机遇是一项具有挑战性的、巨大的、难以置信的努力,因为直觉上吸引人的想法往往伴随着不必要的{ \it副作用},因为它要求我们思考我们深深喜欢的东西。了解当今的大规模算法是如何构建的,对于确定哪些干预措施最有效至关重要。鉴于这些算法严重依赖于{ \it机器学习},我们进行以下关键观察:\emph{any algorithm trained on uncontrolled data must not be trusted}。事实上,恶意实体可以控制数据,用危险的操纵性捏造输入毒害它,从而使训练的算法非常不安全。因此,我们认为,迈向安全和道德的大规模算法的第一步必须是收集可靠的人类判断的大型,安全和值得信赖的数据集。为了实现这一点,我们介绍了\emph{Tournesol},一个开源平台,可在\url{https://tournesol.app}。Tournesol的目标是收集一个大型的人类判断数据库,这些判断是关于算法应该广泛推荐什么(以及它们应该停止广泛推荐什么)。我们概述了Tournesol数据库的结构,Tournesol平台的主要功能以及使其成为一个成功项目必须克服的主要障碍。最重要的是,我们认为,如果成功,Tournesol可能会成为任何安全和道德的大规模算法的重要基础。

英文摘要:

Today's large-scale algorithms have become immensely influential, as they recommend and moderate the content that billions of humans are exposed to on a daily basis. They are the de-facto regulators of our societies' information diet, from shaping opinions on public health to organizing groups for social movements. This creates serious concerns, but also great opportunities to promote quality information. Addressing the concerns and seizing the opportunities is a challenging, enormous and fabulous endeavor, as intuitively appealing ideas often come with unwanted {\it side effects}, and as it requires us to think about what we deeply prefer. Understanding how today's large-scale algorithms are built is critical to determine what interventions will be most effective. Given that these algorithms rely heavily on {\it machine learning}, we make the following key observation: \emph{any algorithm trained on uncontrolled data must not be trusted}. Indeed, a malicious entity could take control over the data, poison it with dangerously manipulative fabricated inputs, and thereby make the trained algorithm extremely unsafe. We thus argue that the first step towards safe and ethical large-scale algorithms must be the collection of a large, secure and trustworthy dataset of reliable human judgments. To achieve this, we introduce \emph{Tournesol}, an open source platform available at \url{https://tournesol.app}. Tournesol aims to collect a large database of human judgments on what algorithms ought to widely recommend (and what they ought to stop widely recommending). We outline the structure of the Tournesol database, the key features of the Tournesol platform and the main hurdles that must be overcome to make it a successful project. Most importantly, we argue that, if successful, Tournesol may then serve as the essential foundation for any safe and ethical large-scale algorithm.

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。

↑