Project Grant FA23862414039

This $255,391 National Science Foundation Technology, Innovation, and Partnerships grant funds Anomalee Inc. to develop a commercially viable prototype for certifying deep neural networks against backdoor attacks. Backdoor attacks maliciously poison AI models to misclassify inputs containing hidden trigger patterns. Anomalee's unsupervised method will mathematically evaluate DNNs for such vulnerabilities without examples of poisoned models or access to training data, addressing a critical need...

This $205,591 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) supports research to understand and mitigate the threat of hardware-based fault attacks on deep neural network (DNN) models. The key research efforts under this award include: Investigating the vulnerability of quantized DNN models to deterministic bit flip attacks on model weights, and the resulting impact on inference...

This $175,000 two-year project grant from the National Science Foundation's Computer and Information Science and Engineering program will fund research at Old Dominion University Research Foundation to advance secure deep learning systems. The awardee will systematically study existing neural network backdoor attacks to understand fundamental attack principles. Based on these findings, the research team will develop algorithms to accurately detect neural backdoors embedded in deep learning...

The Office of Naval Research (ONR) awarded a $249,010 Project Grant to Geovathys Inc. under the Basic and Applied Scientific Research program (CFDA 12.300) to conduct research on features of the geometry of neural networks. The award, which runs from October 1, 2024 to September 30, 2028, aims to stimulate innovative, high-risk research with the potential to advance naval operations and broader scientific knowledge in areas such as materials science, artificial intelligence, and autonomous...

The National Science Foundation Division of Computing and Communication Foundations awarded a $150,000 Project Grant to the Georgia TECH Research Corporation, doing business as the Office Of Sponsored Programs, for collaborative research titled "Foundations of Deep Learning: Theory, Robustness, and the Brain?" from December 1, 2021 through November 30, 2024. The research funded under this award will explore deep learning theory, robustness, and applications for understanding brain...

This five-year, $224,413 National Science Foundation project grant supports research and educational activities to advance the theoretical understanding of overparameterization in deep neural networks. Funded under the NSF's Computer and Information Science and Engineering program, the grant recipient will examine the implications of model overparameterization on deep network performance and robustness. Specific aims include characterizing test set regression and classification performance, as...

This $1,180,000 Project Grant award from the Office of Naval Research under the Basic and Applied Scientific Research program (CFDA 12.300) supports research to develop new algorithms and theoretical foundations for AI systems to deceive adversaries and counter their deceptive tactics. The prime awardee, Georgia Tech Research Corp, will collaborate with the University of California, Santa Barbara; the University of Texas at Austin; and the University of Colorado to carry out the research. Key...

This $100,000 Project Grant award from the Office of Naval Research (ONR) under the Basic and Applied Scientific Research program (CFDA 12.300) supports the University of Maryland, College Park's research on "Reasoning AI Models: Capabilities, Limitations, and Generalization." The five-year award, running from July 1, 2025 to June 30, 2030, will enable UMD to conduct fundamental and applied research on advancing artificial intelligence reasoning capabilities, understanding model...

The Department of the Army Materiel Command Research Development and Engineering Command awarded a $255,240 Project Grant to New York University under the Basic Scientific Research program (CFDA 12.431). The two-year award, made on February 1, 2022 and concluding on January 31, 2024, will support research demonstrating attacks and defenses on autonomous platforms driven by deep networks. The Basic Scientific Research program aims to fund basic research related to improving Army programs and...

This Project Grant from the National Science Foundation's Division of Computing and Communication Foundations, under the Computer and Information Science and Engineering federal grant program (CFDA 47.070), provides $199,999 to support the development of novel algorithms and schemes for ensuring robust operations of deep neural networks. The award to Texas A&M Engineering Experiment Station, doing business as Tees, will fund the Guardiann project from March 1, 2023 through February 28, 2026....