Collaborative Research: CIF-Medium: Privacy-preserving Machine Learning on Graphs

图结构数据捕获不同代理之间的复杂交互，并广泛应用于各种科学和工程应用，如通信理论和计算机科学，医学研究，计算生物学和社会科学。在许多情况下，图形信息是敏感的，必须保持私有。此外，它通常需要更新以适应权限的变化，从而需要从头开始重新训练复杂的大规模机器学习模型。为了同时确保数据保持私密性，并且在不完全重新学习的情况下可以轻松删除，并且其用于进行推理和预测的实用性仍然不受影响，用于图形数据的创新和高效的隐私保护机器学习算法至关重要。除了建立一个新的图形学习方法开发框架外，该项目还将为生物学，物理学和金融图形数据分析的学生提供独特的跨学科培训机会;通过有针对性的招聘和专业学生交流计划，扩大妇女和其他代表性不足的群体在STEM研究中的参与;在这个过程中，在各种机器学习之间建立新的合作，设在参与机构的数据采集和建模中心/研究所。该项目旨在解决设计隐私的基本挑战，通过利用机器学习、数据安全、信息理论、理论计算机科学和统计学等跨学科技术，保存和有效更新图神经网络模型。遇到的主要困难是：（i）图的属性和拓扑结构是异构的，但高度相关的数据类型;（ii）私有化降低了效用;（iii）推理攻击，旨在确定有多少信息泄漏次优私有化图学习者一般是不可靠的。为了解决这些问题，该团队将设计新颖的非统一私有化协议，以不同程度的隐私保护来换取准确性;实施可证明有效的方法来从图神经网络模型中删除图信息，而无需重新训练;在这个过程中，实现了一组新的成员推理方法，可以准确地测量机器学习模型的信息保留和泄漏。该奖项反映了NSF的基金会的使命是履行其法定使命，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。

Graph-structured data captures intricate interactions between diverse agents, and is widespread in various scientific and engineering applications such as communication theory and computer science, medical research, computational biology, and social sciences. In many scenarios, graph information is sensitive and has to be kept private. Additionally, it often necessitates updates to accommodate changes in permissions, leading to the need to retrain sophisticated large-scale machine learning models from the ground up. To simultaneously ensure that the data is kept private and easily removable without complete relearning, and that its utility for making inference and predictions remains uncompromised, innovative, and efficient privacy-preserving machine learning algorithms for graph data are essential. In addition to establishing a framework for novel graph-learning method development, the project will also provide unique cross-disciplinary training opportunities for students in biological, physics, and financial graph data analysis; broaden the participation of women and other under-represented groups in STEM research via targeted recruiting and specialized student exchange programs; and, in the process, establish new collaborations among various machine learning, data acquisition and modeling centers/institutes housed at the participating institutions.This project aims to address fundamental challenges in designing privacy-preserving and efficiently updatable graph neural network models by leveraging interdisciplinary techniques from machine learning, data security, information theory, theoretical computer science and statistics. The main difficulties encountered are that (i) the graph attributes and topology are heterogeneous, yet highly correlated data types; (ii) privatization reduces utility; (iii) inference attacks that aim to determine how much information is leaking for sub-optimally privatized graph learners are generally unreliable. To resolve these issues, the team will devise novel non-uniform privatization protocols that trade accuracy for varied degrees of privacy protection; implement provably efficient methods to remove graph information from graph neural network models without retraining; and in, the process, implement a new cohort of membership inference approaches that can accurately measure information retention and leakage of machine learning 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.