AF: Small: Collaborative Research: New Representations for Learning Algorithms and Secure Computation

AF：小型：协作研究：学习算法和安全计算的新表示

• 批准号: 1907908
• 负责人: Omkant Pandey
• 金额: $ 20万
• 依托单位: SUNY at Stony Brook
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-10-01 至 2022-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1907908&HistoricalAwards=false
• 关键词: AF; Small; Collaborative; Research; New

Recent success of machine learning is due in part to the availability of large datasets for training and testing purposes. However, the training process is computationally intensive and collected datasets are often privacy sensitive. This has led to providing Machine Learning as a Service (MLaaS), where data providers store their data in the cloud and clients purchase trained models or predictions through the cloud. This is an attractive solution, however it requires the data providers to trust the cloud. A compromised cloud can put the privacy of a large population at risk. Existing cryptographic solutions to this problem modify the underlying model of MLaaS and not specifically tailored for machine learning tasks. Accordingly, there is a need for developing secure machine learning procedures, that takes into account both cryptographic and machine learning aspects holistically. This project takes such a holistic approach, focusing on two primary directions: designing machine learning algorithms that are more cryptographic-friendly and new protocols for secure computation in the cloud specialized to machine learning algorithms. As a result, both the state of the art of machine learning and cryptographic research will be advanced thanks to an interdisciplinary approach. This project will support and promote involvement of students from under-represented groups in research. This project has two primary directions: Almost-Linear Machine Learning Components, and Secure Computation over the MLaaS Topology. For the first research goal, the team of researchers aims at finding new representations of learning algorithms that minimize non-linear operations, that are costly for cryptographic algorithms. In particular, this project will focus on a new design for critical machine learning components: stochastic approximation of activation and loss functions that allows to reduce the number of non-linear operations during training and/or testing. This will directly reduce the computational overhead incurred during secure computation. In addition to developing these design principles in depth, the project will also explore techniques for parallelization of certain non-linear components of deep learning, to further amortize cryptographic overhead through batching. At the same time, the aim will be on retaining the guarantees of the machine learning algorithms under modification. For the second research direction, the focus will be on the concept of secure multiparty computation (MPC). A secure MPC protocol is a general method that allows two or more mutually distrustful parties to compute any function over their private inputs so that each party learns nothing beyond its intended output. Traditional MPC protocols are designed for network topologies that are vastly different from the MLaaS topology. Hence, new MPC protocols will be designed, to easily fit the specific needs of machine learning frameworks such as MLaaS. These results will be achieved through the development of two new techniques for secure computation. The first technique will develop a multi-key homomorphic encryption scheme that is simultaneously a decentralized attribute-based encryption. The second technique will develop a new method for extending laconic protocols for oblivious-transfer. Successful development of these techniques will also directly advance the state-of-the-art in homomorphic encryption and secure computation protocols.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.

最近机器学习的成功部分归功于用于训练和测试目的的大型数据集的可用性。然而，训练过程是计算密集型的，收集的数据集通常是隐私敏感的。这导致了机器学习即服务（MLaaS）的出现，数据提供商将数据存储在云中，客户通过云购买经过训练的模型或预测。这是一个很有吸引力的解决方案，但是它要求数据提供者信任云。一个受损的云可能会使大量人口的隐私处于危险之中。针对此问题的现有加密解决方案修改了MLaaS的底层模型，而不是专门为机器学习任务量身定制的。因此，有必要开发安全的机器学习程序，全面考虑密码学和机器学习方面。该项目采用了这样一种整体方法，重点关注两个主要方向：设计更加加密友好的机器学习算法和专门用于机器学习算法的云安全计算的新协议。因此，由于跨学科的方法，机器学习和密码学研究的最新技术都将得到发展。该项目将支持和促进来自代表性不足群体的学生参与研究。该项目有两个主要方向：近线性机器学习组件和基于MLaaS拓扑的安全计算。对于第一个研究目标，研究人员团队的目标是寻找新的学习算法表示，使非线性操作最小化，这对加密算法来说是昂贵的。特别是，该项目将专注于关键机器学习组件的新设计：激活和损失函数的随机近似，可以减少训练和/或测试期间的非线性操作数量。这将直接减少安全计算过程中产生的计算开销。除了深入开发这些设计原则外，该项目还将探索深度学习的某些非线性组件的并行化技术，以通过批处理进一步摊销加密开销。与此同时，其目的将是保留修改后的机器学习算法的保证。第二个研究方向是安全多方计算（MPC）的概念。安全的MPC协议是一种通用方法，它允许两个或多个互不信任的方在其私有输入上计算任何函数，这样每一方都不会知道超出其预期输出的任何东西。传统的MPC协议是为与MLaaS拓扑结构大不相同的网络拓扑结构设计的。因此，新的MPC协议将被设计出来，以轻松满足机器学习框架（如MLaaS）的特定需求。这些结果将通过开发两种新的安全计算技术来实现。第一种技术将开发一种多密钥同态加密方案，该方案同时是一种分散的基于属性的加密。第二种技术将开发一种新的方法来扩展遗忘传输的简洁协议。这些技术的成功发展也将直接推动同态加密和安全计算协议的发展。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。

项目成果

Compact Ring Signatures from Learning With Errors

• DOI: 10.1007/978-3-030-84242-0_11
• 发表时间: 2021
• 作者: Rohit Chatterjee;Sanjam Garg;Mohammad Hajiabadi;Dakshita Khurana;Xiao Liang;Giulio Malavolta;Omkant Pandey;Sina Shiehian

Improved Black-Box Constructions of Composable Secure Computation

改进的可组合安全计算的黑盒结构

• DOI: 10.4230/lipics.icalp.2020.28
• 发表时间: 2020
• 期刊: Leibniz international proceedings in informatics
• 作者: Chatterjee, R.;Liang, X.;Pandey, O.
• 通讯作者: Pandey, O.

A New Approach to Efficient Non-Malleable Zero-Knowledge

高效不可延展零知识的新方法

• 发表时间: 2022
• 期刊: Advances in Cryptology – CRYPTO 2022
• 作者: Kim, A.;Liang, X.;Pandey, O.
• 通讯作者: Pandey, O.

Black-Box Constructions of Bounded-Concurrent Secure Computation

有界并发安全计算的黑盒结构

• DOI: 10.1007/978-3-030-57990-6_5
• 发表时间: 2020
• 期刊: Security and Cryptography for Networks
• 作者: Garg S., Liang X.

Towards a Unified Approach to Black-Box Constructions of Zero-Knowledge Proofs

走向零知识证明黑盒构造的统一方法

• 发表时间: 2021
• 期刊: Advances in Cryptology - CRYPTO 2021
• 作者: Liang, X.;Pandey, O.
• 通讯作者: Pandey, O.