ATD: Algorithmic Threat Detection and Mitigation with Robust Machine Learning

ATD：利用强大的机器学习进行算法威胁检测和缓解

• 批准号: 2027737
• 负责人: Yuekai Sun
• 金额: $ 33万
• 依托单位: Regents of the University of Michigan - Ann Arbor
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2027737&HistoricalAwards=false
• 关键词: ATD; Algorithmic; Threat; Detection; Mitigation

With the recent explosion of scientific data, machine learning (ML) is permeating many areas of science and engineering. Even areas that are traditionally dominated by differential equation models are incorporating ML into their models. However, confidence in and broader adoption of ML in science and engineering face a number of challenges, in large part because existing ML models were developed mostly with non-scientific applications in mind. This project seeks to broaden the appeal of ML in scientific applications (hereafter called scientific ML) by addressing three key issues with existing ML models that are hindering their broader adoption in scientific applications.This project will support one graduate student each year of the three year project. First, we consider how to tailor existing ML models to scientific applications by incorporating (scientific) domain knowledge. In most scientific applications, there is a rich body of domain knowledge to draw upon. If we can properly integrate this knowledge with ML models, it allows the machine to focus on learning less well-understood aspects of the underlying theoretical and physical processes. Ultimately, this not only leads to ML models that can outperform human engineered models, but also to new insights into the underlying physical processes. Second, we consider how to train ML models that are stable and reliable under perturbations in the training data, model choice, and computational errors. ML models are known to be unstable under such perturbations, which undermines their credibility in scientific applications. Third, we focus on training ML models that are capable of predicting the effects of interventions on a system. This is an area in which ML models are lacking compared to traditional differential equation models.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

随着最近科学数据的爆炸式增长，机器学习（ML）正在渗透到科学和工程的许多领域。即使是传统上由微分方程模型主导的领域也将ML纳入其模型中。然而，在科学和工程领域对ML的信心和更广泛的采用面临着许多挑战，这在很大程度上是因为现有的ML模型大多是在考虑非科学应用的情况下开发的。该项目旨在通过解决现有ML模型中阻碍其在科学应用中更广泛采用的三个关键问题，扩大ML在科学应用中的吸引力（以下称为科学ML）。该项目将在为期三年的项目中每年支持一名研究生。首先，我们考虑如何通过整合（科学）领域知识来定制现有的ML模型以适应科学应用。在大多数科学应用中，都有丰富的领域知识可供利用。如果我们能够将这些知识与机器学习模型适当地整合，它将允许机器专注于学习底层理论和物理过程中不太了解的方面。最终，这不仅会导致ML模型的性能优于人类工程模型，还会带来对底层物理过程的新见解。其次，我们考虑如何训练ML模型，使其在训练数据、模型选择和计算误差的扰动下稳定可靠。ML模型在这种扰动下是不稳定的，这破坏了它们在科学应用中的可信度。第三，我们专注于训练能够预测干预对系统影响的ML模型。与传统的微分方程模型相比，这是ML模型所缺乏的领域。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Understanding new tasks through the lens of training data via exponential tilting

• DOI: 10.48550/arxiv.2205.13577
• 发表时间: 2022-05
• 期刊: ArXiv
• 作者: Subha Maity;M. Yurochkin;M. Banerjee;Yuekai Sun

Statistical Inference for Individual Fairness

个人公平性的统计推断

• 发表时间: 2021
• 期刊: International Conference on Learning Representations
• 作者: Maity, Subha;Xue, Songkai;Yurochkin, Mikhail;Sun, Yuekai
• 通讯作者: Sun, Yuekai

On sensitivity of meta-learning to support data

• 发表时间: 2021-10
• 期刊: 2019 IEEE Energy Conversion Congress and Exposition (ECCE)
• 作者: Mayank Agarwal;M. Yurochkin;Yuekai Sun

Outlier-Robust Optimal Transport

• 发表时间: 2020-12
• 作者: Debarghya Mukherjee;Aritra Guha;J. Solomon;Yuekai Sun;M. Yurochkin

Individually Fair Gradient Boosting

单独公平梯度提升

• 发表时间: 2021
• 期刊: International Conference on Learning Representations
• 作者: Vargo, Alexander;Zhang, Fan;Yurochkin, Mikhail;Sun, Yuekai
• 通讯作者: Sun, Yuekai