Project Grant 2450935
Award Date 10/1/25
Completion Date 9/30/29
Dollars Obligated $220K
Funding Federal Agency
Awarding Federal Agency
Federal Grant Program
Assistance Type
Project Grant
Place of Performance
Durham, NC 27705, USA
Similar Awards
- This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Project Grant for $150,000, awarded on October 1, 2025, supports research to secure large language model (LLM) applications against prompt injection attacks. The project, led by the University of California, Berkeley, will conduct a systematic study to deepen the understanding of such threats and develop new defenses to mitigate these attacks. The project aims to establish foundational security...
- This $180,000 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program will support a collaborative research project at The Pennsylvania State University (Penn State) to study and develop new defenses against prompt injection attacks on large language models (LLMs). 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...
- This Project Grant award, valued at $249,956.00, was provided by the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) and is focused on developing a cybertraining program to train undergraduate and graduate students across the nation to identify, analyze, and mitigate different attack vectors targeting large language model (LLM)-empowered advanced cyberinfrastructure (CI) systems. The program will consist of eight...
- This $331,428 federal Project Grant award was provided by the National Science Foundation (NSF) Computer and Information Science and Engineering (CFDA 47.070) program to the University of Maryland, College Park. The grant supports research to develop techniques for ensuring the security and correctness of code generated by large language models (code LLMs), which are becoming integral to AI-driven software development. Specifically, the project aims to establish a foundation for evaluating the...
- This $369,693 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program aims to transform cybersecurity defenses against advanced persistent threats (APTs) by leveraging large language models (LLMs). The 5-year project, awarded to Virginia Polytechnic Institute & State University, will develop an LLM-powered framework to enhance cyber threat detection, investigation, and collaboration between human experts and automated...
- This National Science Foundation (NSF) Project Grant award under the Computer and Information Science and Engineering (CFDA 47.070) program supports research to expand the understanding of large language models (LLMs), a type of artificial intelligence (AI) system. The $471,529 award to Trustees of Boston University aims to develop methods for identifying and characterizing multi-dimensional and continuous internal representations within LLMs, rather than just simple binary concepts. This work...
- This Project Grant award from the National Science Foundation's Computer and Information Science and Engineering program (CFDA 47.070) provides $262,900 to Portland State University over the period of October 1, 2023 to September 30, 2025. The goal of this project is to redesign security education curricula to better integrate and leverage the use of large language models (LLMs) in addressing modern cybersecurity challenges. The key objectives are to create new educational content and lab...
- The National Science Foundation (NSF) awarded a $431,250 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) program to Carnegie Mellon University (CMU) to develop principled defenses against vulnerabilities in modern machine learning (ML) systems. The goal is to make robustness a core design property rather than an afterthought, bridging rigorous analysis with practical experimentation. The project will proceed along three technical thrusts: 1) robust...
- This Project Grant award from the National Science Foundation (CFDA 47.070 - Computer and Information Science and Engineering) provides $266,000.00 to Wayne State University to advance research on large language model (LLM) unlearning. The project aims to develop new algorithmic frameworks, model interpretability approaches, and data handling techniques to enable the targeted removal of harmful data influences and behaviors from pretrained LLMs without compromising their overall performance. Key...
- The National Science Foundation (NSF) awarded a $266,000 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) program to The Leland Stanford Junior University (Stanford University) to advance research in Large Language Model (LLM) unlearning. The project aims to develop new algorithmic frameworks, model interpretability approaches, and data management techniques to enable the targeted removal of harmful content and behaviors from pretrained LLMs without...