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

图结构数据捕获了不同主体之间复杂的相互作用，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，必须保密。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型机器学习模型。为了同时确保数据的私密性和易于删除，而无需完全重新学习，并且其用于进行推理和预测的效用仍然不受损害，创新和有效的保护隐私的机器学习算法对于图数据至关重要。除了建立新的图形学习方法开发框架外，该项目还将为学生提供生物，物理和金融图形数据分析方面的独特跨学科培训机会；通过有针对性的招聘和专门的学生交流项目，扩大女性和其他代表性不足群体在STEM研究中的参与；在此过程中，在参与机构的各种机器学习、数据采集和建模中心/研究所之间建立新的合作关系。该项目旨在通过利用机器学习、数据安全、信息论、理论计算机科学和统计学等跨学科技术，解决设计隐私保护和有效更新图神经网络模型的基本挑战。遇到的主要困难是：(i)图属性和拓扑是异构的，但高度相关的数据类型；私有化降低了效用；（iii）旨在确定次最优私有化图学习器泄露了多少信息的推理攻击通常是不可靠的。为了解决这些问题，该团队将设计新的非统一私有化协议，以准确性换取不同程度的隐私保护；实现可证明的有效方法，从图神经网络模型中去除图信息，而无需再训练；在此过程中，实现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。该奖项反映了美国国家科学基金会的法定使命，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。

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.