Collaborative Research: SHF: ZEAL: Zero-Knowledge Proof Acceleration Leveraging Hardware-Software Co-Design

This project focuses on a powerful privacy technology known as Zero-Knowledge Proofs (ZKPs). ZKPs allow one party to prove that a computation or transaction is valid without revealing the underlying private information. One important type of ZKP is called a Zero-Knowledge Succinct Non-Interactive Argument of Knowledge. These technologies are becoming essential for applications such as digital currencies, fraud prevention, secure online identity systems, and trustworthy AI. For example, a bank could prove it has sufficient reserves without revealing customer information, or an AI provider could prove that a model was trained correctly without exposing proprietary data. Although ZKPs offer strong privacy and security guarantees, they currently require enormous computing power and memory, making them too slow and expensive for widespread real-world use. Existing software solutions running on conventional computer processors struggle to support the speed and scale needed for high-volume financial systems and real-time AI applications. The goal of this project is to design faster and more energy-efficient computing systems specifically optimized for privacy-preserving cryptographic operations. The research team will develop new hardware and software technologies that work together to accelerate these computations while remaining flexible enough to support evolving cryptographic standards and applications. This includes exploring Processing-in-Memory (PIM) architectures, where computation is performed closer to where data is stored, reducing the time and energy required to move data between memory and processors. By reducing processing time and energy consumption, the project aims to make privacy-preserving technologies practical for everyday use. 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.