Collaborative Research: SaTC: CORE: Small: Securing Brain-inspired Hyperdimensional Computing against Design-time and Run-time Attacks for Edge Devices

协作研究：SaTC：核心：小型：保护类脑超维计算免受边缘设备的设计时和运行时攻击

• 批准号: 2326597
• 负责人: Xiaolin Xu
• 金额: $ 30万
• 依托单位: Northeastern University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-10-01 至 2026-09-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2326597&HistoricalAwards=false
• 关键词: Collaborative; Research; SaTC; CORE; Small

Many computing applications depend on machine learning (ML) algorithms that analyze patterns in data and make predictions about new data they encounter. Many recent advances in these machine learning classifiers use approaches based on neural networks; however, neural networks often require large amounts of data, memory, and processing power. Brain-inspired hyperdimensional computing (HDC) has emerged in recent years as a less resource-heavy approach to building classifiers that are well-suited for smaller computing devices that have less computing power. However, just like other ML classifier architectures, HDC models may be threatened by attackers who want to degrade the models' performance, insert backdoor "triggers" that let attackers take control of devices by presenting secret inputs, or steal the models themselves. However, these security risks in HDC models are not as well-studied as HDC performance. This project's goal is to close that gap through a better understanding of HDC security vulnerabilities and defenses. This includes analyzing the space of possible attacks on HDC models, drawing parallels between attacks and defenses in neural networks and those in HDC models, and developing defenses that are as effective, efficient, and lightweight as the HDC models themselves so they can too be deployed in devices with limited computing power.This project paves the way for HDC-based inference on edge devices by systematically investigating the attack surface for HDC computing, from design time to run time and from algorithm to hardware. First, it explores the vulnerabilities associated with HDC and systematically defines its unique attack surface. Accordingly, it investigates critical threats against HDC model performance and privacy from adversarial input, model perturbation, and reverse engineering. Second, it explores effective and efficient defense strategies by incorporating algorithmic-, hardware-, and system-level methods. A key insight and tool in the proposed work are methods for relating neural network-based models and HDC models; this will allow for comparative studies as well as open possibilities for adapting existing attacks and defenses on neural network-based architectures to HDC contexts. The scientific outcomes will help reshape HDC-enabled computing systems toward greater security and robustness. The project also contains a significant educational component and provides abundant opportunities to nurture and attract students from under-represented groups to engage in computer science and computer science research.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.

许多计算应用程序依赖于机器学习 (ML) 算法来分析数据模式并对遇到的新数据进行预测。这些机器学习分类器的许多最新进展都使用基于神经网络的方法；然而，神经网络通常需要大量数据、内存和处理能力。近年来，受类脑启发的超维计算（HDC）作为一种资源消耗较少的方法来构建分类器，非常适合计算能力较低的小型计算设备。然而，就像其他 ML 分类器架构一样，HDC 模型可能会受到攻击者的威胁，他们想要降低模型的性能、插入后门“触发器”，让攻击者通过提供秘密输入来控制设备，或者窃取模型本身。然而，HDC 模型中的这些安全风险并未像 HDC 性能那样得到充分研究。该项目的目标是通过更好地了解 HDC 安全漏洞和防御来缩小这一差距。这包括分析 HDC 模型可能受到攻击的空间，将神经网络中的攻击和防御与 HDC 模型中的攻击和防御进行比较，以及开发与 HDC 模型本身一样有效、高效和轻量级的防御，以便它们也可以部署该项目通过系统地研究 HDC 计算的攻击面（从设计时到运行时、从算法到硬件），为边缘设备上基于 HDC 的推理铺平了道路。首先，它探讨了与 HDC 相关的漏洞，并系统地定义了其独特的攻击面。因此，它调查了来自对抗性输入、模型扰动和逆向工程对 HDC 模型性能和隐私的关键威胁。其次，结合算法、硬件、系统层面的方法，探索有效、高效的防御策略。拟议工作中的一个关键见解和工具是将基于神经网络的模型和 HDC 模型相关联的方法；这将允许进行比较研究，并为将基于神经网络的架构的现有攻击和防御适应 HDC 环境提供开放的可能性。这些科学成果将有助于重塑支持 HDC 的计算系统，以实现更高的安全性和鲁棒性。该项目还包含重要的教育内容，并提供丰富的机会来培养和吸引弱势群体的学生从事计算机科学和计算机科学研究。该奖项反映了 NSF 的法定使命，并通过使用基金会的评估进行评估，认为值得支持。智力价值和更广泛的影响审查标准。

项目成果

AQ2PNN: Enabling Two-party Privacy-Preserving Deep Neural Network Inference with Adaptive Quantization

AQ2PNN：通过自适应量化实现两方隐私保护深度神经网络推理

• DOI: 10.1145/3613424.3614297
• 发表时间: 2023-10
• 期刊: ACM
• 作者: Luo, Yukui;Xu, Nuo;Peng, Hongwu;Wang, Chenghong;Duan, Shijin;Mahmood, Kaleel;Wen, Wujie;Ding, Caiwen;Xu, Xiaolin
• 通讯作者: Xu, Xiaolin

MirrorNet: A TEE-Friendly Framework for Secure On-Device DNN Inference

MirrorNet：用于安全设备上 DNN 推理的 TEE 友好框架

• DOI: 10.1109/iccad57390.2023.10323746
• 发表时间: 2023-10
• 期刊: IEEE
• 作者: Liu, Ziyu;Luo., Yukui;Duan, Shijin;Zhou, Tong;Xu, Xiaolin
• 通讯作者: Xu, Xiaolin

Achieving Certified Robustness for Brain-Inspired Low-Dimensional Computing Classifiers

实现类脑低维计算分类器的鲁棒性认证

• DOI: 10.1109/infocomwkshps57453.2023.10225774
• 发表时间: 2023-05
• 期刊: IEEE INFOCOM 2023 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS
• 作者: Yang, Fangfang;Duan, Shijin;Xu, Xiaolin;Ren, Shaolei
• 通讯作者: Ren, Shaolei