Collaborative Research: SaTC: CORE: Small: Secure and Robust Machine Learning in Multi-Tenant Cloud FPGA

协作研究：SaTC：CORE：小型：多租户云 FPGA 中安全且稳健的机器学习

基本信息

批准号：
2153525
负责人：
Deliang Fan
金额：
$ 25万
依托单位：
Arizona State University
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2022
资助国家：
美国
起止时间：
2022-07-15 至 2024-04-30
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=2153525&HistoricalAwards=false
关键词：
Collaborative Research SaTC CORE Small

项目摘要

Alongside the rapid growth of cloud-computing market and critical developments in machine learning (ML) computation, the cloud-FPGA (Field Programmable Gate Arrays) has become a vital hardware resource for public lease, where multiple tenants can co-reside and share an FPGA chip over time or even simultaneously. With many hardware resources being jointly used in the multi-tenant cloud-FPGA environment, a unique attack surface is created, where a malicious tenant can leverage such indirect interaction to manipulate the circuit application of other tenants, e.g., intentionally injecting faults. It has been demonstrated in prior research that small, but carefully designed, perturbation of the ML model parameter transmission between off-chip memory and on-chip buffer could completely malfunction ML intelligence, even under black-box attack scenario, posing an unprecedented threat to future ML cloud-FPGA system. This project (1) targets to understand the vulnerability of multi-tenant ML cloud-FPGA systems and explore defensive approaches, which are crucial and timely for both industry and academia in the cloud-FPGA computing domain; (2) advances the security of ML cloud system against hardware-based model tampering on off-chip data transmission in multi-tenant cloud-FPGA computing infrastructure; and (3) integrates the research outcomes with education in terms of new curriculum development, undergraduate and graduate student training, as well as promoting women and underrepresented minorities in STEM through K-12 outreach programs. This project integrates ML algorithm security and FPGA hardware security to follow a software-hardware co-design mechanism, exploring novel solutions that improve the security of multi-tenant ML cloud-FPGA system. It consists of three research thrusts. Thrust-1 systematically studies, models, and characterizes an adversarial weight duplication hardware fault injection method, which leverages aggressive power-plundering circuits in malicious tenant to inject fault into the victim tenant's ML model. Thrust-2 explores various ML algorithmic methodologies to enhance the intrinsic robustness and resiliency of ML model against adversarial fault injection into model parameters during the transmission from off-chip memory to on-chip buffer. Thrust-3 investigates FPGA system-level tamper-resistant approaches to further provide comprehensive solutions to improve the ML-FPGA system security.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.

随着云计算市场的快速增长和机器学习（ML）计算的关键发展，云FPGA（现场可编程门阵列）已成为公共租赁的重要硬件资源，多个租户可以共住并共享一个公共空间。 FPGA芯片随着时间的推移甚至同时发生。由于许多硬件资源在多租户云-FPGA环境中联合使用，因此创建了独特的攻击面，恶意租户可以利用这种间接交互来操纵其他租户的电路应用，例如故意注入故障。先前的研究已经证明，即使在黑盒攻击的情况下，片外存储器和片上缓冲区之间的 ML 模型参数传输的微小但精心设计的扰动也可能使 ML 智能完全失灵，从而对机器学习构成前所未有的威胁。未来的ML云-FPGA系统。该项目（1）旨在了解多租户ML云-FPGA系统的漏洞并探索防御方法，这对于云-FPGA计算领域的工业界和学术界都至关重要且及时； (2) 提高ML云系统的安全性，防止多租户云-FPGA计算基础设施中片外数据传输的基于硬件的模型篡改； (3) 将研究成果与新课程开发、本科生和研究生培训以及通过 K-12 推广计划促进女性和代表性不足的少数族裔在 STEM 领域的教育相结合。该项目将机器学习算法安全性和FPGA硬件安全性相结合，遵循软硬件协同设计机制，探索提高多租户机器学习云-FPGA系统安全性的新颖解决方案。它由三个研究重点组成。 Thrust-1 系统地研究、建模和描述了一种对抗性权重复制硬件故障注入方法，该方法利用恶意租户中的攻击性电力掠夺电路，将故障注入受害租户的 ML 模型中。 Thrust-2 探索了各种 ML 算法方法，以增强 ML 模型的内在鲁棒性和弹性，以防止在从片外存储器传输到片上缓冲区期间将对抗性故障注入到模型参数中。 Thrust-3 研究 FPGA 系统级防篡改方法，以进一步提供全面的解决方案来提高 ML-FPGA 系统安全性。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力优势和更广泛的影响审查进行评估，认为值得支持标准。