Project Grant 2428949
- The National Science Foundation (NSF) awarded a $420,000 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) program to New York University (NYU) to evaluate the security landscape of machine learning (ML) and artificial intelligence (AI) technologies used in electronic design automation (EDA) tools for chip design. The 3-year project aims to: (1) comprehensively analyze the impact of input and training data perturbations and attacks on the quality,...
- This $166,667 federal Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program will support research to uncover the mathematical, statistical, and contextual mechanisms behind memorization in artificial intelligence (AI) models. The key objectives are to develop computationally efficient metrics for quantifying memorization, leverage optimization theory, dynamical systems theory, and information theory to gain insights...
- This NSF CISE (CFDA 47.070) $600,000 Project Grant awarded to The Pennsylvania State University, doing business as Penn State, will develop methods to reduce privacy risks while enabling users to benefit from high-quality AI-based services. The key goals are to create mathematically-guaranteed privacy-preserving encodings or embeddings that can be used as input for AI-based applications, such as artistic image generation, medical diagnosis, and assistive technologies for the visually impaired....
- This $299,886 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program aims to develop new big data algorithms that are robust to adversarial input. The award supports research to address emerging vulnerabilities in areas such as black-box streaming algorithms, white-box streaming algorithms, and adaptive data analysis with bounded space. This work will focus on improving the reliability, security, and trustworthiness of...
- This Project Grant award of $438,871 from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program, with an award date of October 1, 2025 and a completion date of September 30, 2030, aims to address emerging security and ethical challenges in AI-integrated crowdsourcing. The key objectives of the project are: Developing trustworthy human-AI collaborative annotation systems by improving robustness against adversarial inputs, including...
- This Project Grant award, titled "COLLABORATIVE RESEARCH: SATC: CORE: SMALL: EVALUATING THE SECURITY LANDSCAPE OF MACHINE LEARNING ENABLED ELECTRONIC DESIGN AUTOMATION", was provided by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070). The $180,000 award will support research at Arizona State University (ASU) from October 1, 2025 to September 30, 2028. The project will comprehensively assess...
- This Project Grant award, titled "CRII: SATC: TOWARDS DATA-EFFECTIVE AND COST-EFFICIENT SECURITY ATTACK DETECTIONS", was provided by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070). The award, totaling $117,019.00, was made to the Rochester Institute of Technology on August 15, 2025 and is scheduled for completion on February 28, 2026. The primary objectives of this project are to explore new...
- The National Science Foundation (NSF) awarded a $600,000 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) program to the University of South Carolina. The grant, with a period of performance from October 1, 2024 to September 30, 2027, focuses on enhancing security and mitigating harm in AI-generated vision language models. Key technical objectives include: 1) Developing a prompting framework for detecting harmful content provenance in AI-generated vision...
- This $250,000 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE, CFDA #47.070) program supports a workshop and issue paper to develop a forward-looking research agenda for securing artificial intelligence (AI) systems. The National Academies of Sciences, Engineering, and Medicine will convene experts across the research community to systematically assess current and emerging threats to AI systems, as well as the risks...
- This $150,000 Project Grant awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) program supports a collaborative research initiative focused on securing large language models (LLMs) against prompt injection attacks. The key objectives of this 4-year project are to: (1) conduct a systematic study to deepen the understanding of security vulnerabilities in LLM-integrated applications arising from the lack of clear boundaries between...
This $520,000 federal Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program investigates security and privacy vulnerabilities in embedding-based AI systems. The project, titled "SATC: CORE: SMALL: SECURING EMBEDDINGS," will tackle security issues related to the fundamental building blocks of modern AI - embeddings that convert data into mathematical vector representations. The research will focus on defending against adversarial attacks that can manipulate large language models or extract private information from vector databases. The award, effective from January 1, 2026 to December 31, 2028, aims to develop robust mitigations to ensure the trustworthy deployment of AI-powered systems in our digital society.
Mod # | Description | ReasonForModification | Federal Obligation | Date |
|---|---|---|---|---|
| Not listed | $520.0k | 12/4/25 |