Project Grant 2153690
Award Date
7/15/22
Completion Date
6/30/25
Dollars Obligated
$250K
Federal Agency
Division of Computer and Network Systems
Federal Grant Program
47.070
Assistance Type
Project Grant
Place of Performance
Boston, MA 02115, USA
Similar Awards
This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Award (CFDA 47.070) provides $246,516 to Arizona State University (ASU) to conduct research on securing machine learning models in multi-tenant cloud FPGA (field programmable gate array) environments. The project aims to: (1) understand the vulnerabilities of multi-tenant machine learning cloud-FPGA systems and explore defensive approaches; (2) advance the security of machine learning...
The National Science Foundation (NSF) awarded a $299,995 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) program to the University of Massachusetts (UMass) to develop novel security approaches for protecting field-programmable gate arrays (FPGAs) used in cloud computing environments. The key objectives of this 3-year project are to introduce secure operating mechanisms and a security and queue management unit (SQMU) to enable controlled sharing of FPGAs...
This four-year $300,000 Project Grant from the National Science Foundation's Computer and Information Science and Engineering program aims to develop secure foundations for federated learning. Federated learning enables machine learning models to be collaboratively trained using data from many client devices without sharing private information. The researchers will investigate security vulnerabilities in federated learning's training phase, such as poisoning and backdoor attacks. They will...
This two-year, $600,000 Project Grant from the National Science Foundation's Computer and Information Science and Engineering program aims to advance side-channel analysis and protection through deep learning techniques. Funded research at Northeastern University will develop novel methods for applying deep neural networks to both microarchitectural side-channel attacks and effective countermeasures. Key products include a persistent cache monitoring mechanism to improve observation of victim...
This National Science Foundation award provides $498,003 to Arizona State University under the Computer and Information Science and Engineering program to develop security countermeasures for field-programmable gate array (FPGA)-as-a-service systems. The university will conduct research on authentication methods, information flow tracking, formal methods, and machine learning to detect malicious FPGA bitstreams. Evaluation will utilize Xilinx Kintex-7 and Zynq-7000 FPGAs to develop benchmarks...
This Project Grant award from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) provides $247,059 to the University of California, Santa Cruz (UCSC) to conduct collaborative research on securing cloud-based Field Programmable Gate Arrays (FPGAs) from analog temporal side-channel attacks. The project aims to study, characterize, and develop mitigations for data leakage between subsequent FPGA users through an analog side-channel...
This Project Grant award from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) totaling $225,934 supports research to characterize and mitigate "FPGA pentimenti" - analog data leakage between subsequent users of cloud-based field programmable gate arrays (FPGAs). The project, conducted by the University of California, San Diego (UCSD), aims to establish the bounds of data recovery capabilities within the cloud FPGA...
This $194,726 two-year Project Grant from the National Science Foundation's Engineering program (CFDA 47.041) will fund research at Worcester Polytechnic Institute on machine learning techniques for assessing hardware security against side-channel attacks. The grantee will develop novel approaches using deep learning theoretical foundations to evaluate cryptosystems' resilience to machine learning-enhanced side-channel analysis on real-world implementations. The research aims to address...
This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) project grant award, with CFDA Number 47.070, supports research to study and mitigate "FPGA pentimenti" - the unintended data leakage between subsequent users of cloud-based Field Programmable Gate Array (FPGA) hardware accelerators. The $189,509 award to the University of Washington aims to characterize the analog side-channel effects leading to this data leakage, establish bounds on the...
This Project Grant award, valued at $205,591.00, was provided by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program. The goal of the project is to investigate and develop techniques to secure deep learning systems against hardware-based model tampering attacks, which can cause catastrophic impacts on security and safety-critical applications. The research efforts will focus on: (1) examining the vulnerability of quantized deep...