Research Initiation Award: Hardware-integrated DNN Intellectual Property Protection Framework Based on Active Locking and Protection
- Institution
- Howard University, DC
- Principal investigator
- Wenjie Che
- Funding
- $450K
- Duration
- 2026–2029
Moonbase score
Still being scored
Abstract
The Historically Black Colleges and Universities Undergraduate Program (HBCU-UP) through Research Initiation Awards (RIA) provide support for junior and mid-career faculty at Historically Black Colleges and Universities who are building new research programs or redirecting and rebuilding existing research programs. It is expected that the award will help to further the faculty member's research capability and effectiveness and improve research and teaching at the home institution. This award supports research to strengthen the security of artificial intelligence (AI) technologies by developing new approaches to protect the intellectual property of deep neural network (DNN) models deployed as edge devices. As AI is increasingly deployed in applications that affect everyday life, protecting these models from unauthorized access and misuse in becoming increasingly important to ensure the security, reliability, and trustworthiness of AI-enabled systems. This project also strengthens research capacity at Howard University by expanding faculty research and providing undergraduate and graduate students with research and training opportunities in AI and hardware security, contributing to the development of a skilled STEM workforce. The project aims to develop a hardware-integrated framework for protecting the intellectual property of DNN models deployed on edge devices. The research investigates active model locking and per-device unlocking mechanisms that integrate fault attack techniques, cryptographic approaches, and hardware security fingerprints to improve protection against unauthorized access. The proposed research advances knowledge at the intersection of AI and hardware security by developing implementation-efficient and attack-resistant approaches for securing deployed DNN models. By advancing secure AI technologies and preparing a skilled STEM workforce, the project contributes to the nation’s scientific and technological competitiveness. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
LOADING MOONBASE SCORE
Questions for Howard University
Answered by the team behind this research.
No questions yet. Sign in to ask the first one
Related grants
Same researchers, same institution, same topic, scored first.
- NSF · Howard UniversityNot yet scored
Collaborative Research: CISE Crosscutting Small: SaTC: SAGE: Secure Accelerators for Next-Generation Foundation Models
Wenjie Che · $325K · 2025–2028
- NIH · Howard University73
Neuregulin-1 as a Therapeutic Treatment of Ischemic Stroke
Byron D. Ford · $373K · 1997–2029
- NIH · Howard University65
Platform for Analyzing the Mutations associated with Schizophrenia (PAMS)
Shaolei Teng · $137K · 2025–2029