CCRI: ENS: Enhancement of Trust-Hub, a Web-based Portal to support the Cybersecurity Research Community

CCRI：ENS：增强 Trust-Hub，这是一个支持网络安全研究社区的基于 Web 的门户网站

• 批准号: 2016737
• 负责人: Farinaz Koushanfar
• 金额: $ 40.49万
• 依托单位: University of California-San Diego
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-07-15 至 2023-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2016737&HistoricalAwards=false
• 关键词: CCRI; ENS; Enhancement; Trust; Hub

Concerns about electronic hardware and supply chain security have received a tremendous amount of attention over the past decade or so. Although researchers have offered solutions and security mechanisms to mitigate the issues, they do not still evaluate their effectiveness in a systematic manner. Some research is still being carried out in an ad-hoc fashion where the published results rely on figures of merit that limit objective cross-field comparisons. However, this has become vital as system-on-chips (SoCs) become pervasive in virtually every application (mobile, internet of things (IoT), and critical systems). This project aims to build platforms to validate benchmarks, develop tools and metrics to validate SoC security, and create a web-portal to disseminate and promote research and development in securing electronics devices and systems. The intellectual merits of this project include development of (i) a comprehensive SoC vulnerability database, (ii) a comprehensive set of metrics based on the vulnerability database, (iii) SoC security validation tool suite, and (iv) SoC benchmarking. This project leads a community-wide framework, called the Trust-Hub, toward stronger assurances in SoCs, computational platforms, and the electronics supply chain. Based on the demonstrated success of information sharing, Trust-Hub will serve as an important web-based repository for benchmarks, tools, databases, platforms, evaluation software, source codes, and much more.The results will interest major semiconductor companies, US government agencies and university researchers worldwide. The broader impacts include benefits to the society by building secure and trustworthy electronic devices and systems for healthcare, defense, military, space, finance, transportation, automotive and other critical applications. The scientific results will be presented to the hardware and electronics security community, and to semiconductor companies and government agencies. Students will use the benchmarks and tools in the annual competitions. Finally, this project will support development of a workforce who understand the much-needed protection of electronics supply chain and intellectual property (IP).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.

在过去十年左右的时间里，对电子硬件和供应链安全的担忧受到了极大的关注。尽管研究人员已经提供了解决方案和安全机制来缓解这些问题，但他们仍然没有系统地评估它们的有效性。一些研究仍在以特别的方式进行，已发表的结果依赖于限制客观跨领域比较的优点系数。然而，随着片上系统(SoC)在几乎所有应用(移动、物联网(IoT)和关键系统)中普及，这一点变得至关重要。该项目旨在建立验证基准的平台，开发验证SoC安全的工具和指标，并创建一个门户网站来传播和促进电子设备和系统安全方面的研究和开发。该项目的智力优势包括开发(I)全面的SoC漏洞数据库，(Ii)基于漏洞数据库的一套全面的度量标准，(Iii)SoC安全验证工具套件，以及(Iv)SoC基准测试。该项目领导一个称为信任中心的社区范围的框架，在SoC、计算平台和电子供应链中实现更强有力的保证。基于已证明的信息共享的成功，Trust-Hub将成为基准、工具、数据库、平台、评估软件、源代码等的重要网络存储库。其结果将引起世界各地的主要半导体公司、美国政府机构和大学研究人员的兴趣。更广泛的影响包括为医疗、国防、军事、航天、金融、交通、汽车和其他关键应用构建安全可靠的电子设备和系统，从而为社会带来好处。科学成果将提交给硬件和电子安全界，以及半导体公司和政府机构。学生将在年度比赛中使用基准和工具。最后，该项目将支持一支了解电子供应链和知识产权(IP)亟需保护的劳动力队伍的发展。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标准进行评估，被认为值得支持。

项目成果

Intellectual Property Protection of Deep Learning Systems via Hardware/Software Co-design

通过软硬件协同设计保护深度学习系统的知识产权

• DOI: 10.1109/mdat.2023.3303435
• 发表时间: 2023
• 期刊: IEEE Design & Test
• 影响因子: 2
• 作者: Chen, Huili;Fu, Cheng;Rouhani, Bita Darvish;Zhao, Jishen;Koushanfar, Farinaz
• 通讯作者: Koushanfar, Farinaz

AutoRank: Automated Rank Selection for Effective Neural Network Customization

• DOI: 10.1109/jetcas.2021.3127433
• 发表时间: 2021-12
• 期刊: IEEE Journal on Emerging and Selected Topics in Circuits and Systems
• 影响因子: 4.6
• 作者: Mojan Javaheripi;Mohammad Samragh;F. Koushanfar

SenseHash: Computing on Sensor Values Mystified at the Origin

• DOI: 10.1109/tetc.2022.3217488
• 发表时间: 2024-04
• 期刊: IEEE Transactions on Emerging Topics in Computing
• 影响因子: 5.9
• 作者: Nojan Sheybani;Xinqiao Zhang;S. Hussain;F. Koushanfar

AccHashtag: Accelerated Hashing for Detecting Fault-Injection Attacks on Embedded Neural Networks

• DOI: 10.1145/3555808
• 发表时间: 2022-08
• 期刊: ACM Journal on Emerging Technologies in Computing Systems
• 影响因子: 2.2
• 作者: Mojan Javaheripi;Jung-Woo Chang;F. Koushanfar

Scalable Binary Neural Network applications in Oblivious Inference

可扩展的二元神经网络在遗忘推理中的应用

• DOI: 10.1145/3607192
• 发表时间: 2023
• 期刊: ACM Transactions on Embedded Computing Systems
• 影响因子: 2
• 作者: Zhang, Xinqiao;Samragh, Mohammad;Hussain, Siam;Huang, Ke;Koushanfar, Farinaz
• 通讯作者: Koushanfar, Farinaz