Project Grant 2212457
Award Date
10/1/22
Completion Date
9/30/25
Dollars Obligated
$900K
Federal Agency
Division of Computing and Communication Foundations
Federal Grant Program
47.070
Assistance Type
Project Grant
Place of Performance
Baltimore, MD 21218, USA
Similar Awards
This three-year $300,000 project grant from the National Science Foundation's Computer and Information Science and Engineering program aims to advance understanding of robustness in machine learning models. Specifically, the University of Maryland, College Park will research conditions under which adversarial attacks on deep networks can be detected and original data reconstructed. It will also study fundamental limits of robustness guarantees against poisoning attacks, especially with a...
This $300,000 National Science Foundation project grant supports research into robust machine learning under sparse adversarial attacks through 2025. Funded under the Computer and Information Science and Engineering program (CFDA 47.070), the University of California, Santa Barbara will develop theoretical frameworks and defense methods to make machine learning models resilient against perturbations affecting few data points. Specifically, the researchers aim to establish fundamental limits of...
This $160,118 federal Project Grant award from the National Science Foundation's (NSF) Mathematical and Physical Sciences program will support The Johns Hopkins University in developing fast and accurate machine learning algorithms with interpretable mechanisms for learning from complex datasets. The project aims to close the theoretical and computational gap between data-independent and data-adaptive random partitioning methods in machine learning, by utilizing and expanding the toolkit of...
This $316,672 Project Grant awarded by the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program supports research at San Diego State University Foundation to develop a comprehensive understanding of the robustness and computational efficiency of deep neural networks. The key focus areas include: 1) formulating theoretical frameworks for subnetwork adversarial robustness, 2) characterizing transferability through curriculum learning, and 3)...
This National Science Foundation (NSF) Project Grant award provides $399,994 to The Johns Hopkins University from July 1, 2023 to June 30, 2026. The grant is funded under the NSF's Computer and Information Science and Engineering program (CFDA 47.070), which supports research and education in computing, communications, and information science. The project aims to develop a rigorous mathematical theory to explain the phenomenon of "neural collapse" in deep learning models, and use...
This $299,998 federal Project Grant award from the National Science Foundation's Computer and Information Science and Engineering (CFDA 47.070) program will support collaborative research at Carnegie Mellon University to develop new big data algorithms that are robust to adversarial input. The key focus areas include: 1) adversarial robustness in black-box and white-box streaming settings, and 2) adaptive data analysis with bounded space. The research team will also explore emerging attack...
This $271,343 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) supports research into developing robust machine learning and inference methods that can withstand data corruption and distribution shifts. The project aims to explore new techniques for structured learning, supervised learning, and reinforcement learning that are resilient to these challenges, with potential applications in healthcare,...
The National Science Foundation Division of Information and Intelligent Systems awarded a $399,923 project grant to The Johns Hopkins University from September 2021 through August 2024. This funding supports research titled "CAUSAL AND SEMI-PARAMETRIC INFERENCE FOR EXPLANATIONS OF DISPARITIES AND DISPARITY-CORRECTING MODELING" under the NSF's Computer and Information Science and Engineering program (CFDA 47.070). The goal of this project grant is to advance the development of causal...
This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) provides $524,981 to Northeastern University to develop novel methods and tools for investigating and defending against machine learning (ML) poisoning attacks on cyber networks. The project aims to create explanation-based ML and generative modeling techniques to identify stealthy poisoning attacks against supervised, semi-supervised, and...
The National Science Foundation (NSF) awarded a $331,063 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) federal grant program to North Carolina State University (NC State). The grant aims to develop transformative methods to enhance the resilience and reliability of machine learning (ML) systems in dynamic, real-world environments. Specifically, the project will: 1) Enhance robustness generalization across data distributions to mitigate robustness...