NYU Tandon researcher wins NSF CAREER Award to support the acceleration of privacy-preserving computation

Brandon Reagen

Brandon Reagen, Assistant Professor of Electrical and Computer Engineering as well as Computer Science and Engineering, has earned an NSF Career Award, one of the most prestigious recognitions for young researchers. The award supports early-career faculty who have the potential to serve as academic role models in research and education. 

A five-year NSF grant of $500,000 will support his fundamental research aimed at creating hardware and compilers to accelerate privacy-preserving computation, including fully homomorphic encryption, which enables computation on encrypted data, or ciphertext, to keep data protected at all times.

He joins the over 50% of NYU Tandon’s engineering faculty members who hold CAREER Awards or similar young-investigator honors, including 12 just since 2019.

Reagen, who is also a member of the NYU Center for Cybersecurity, focuses his research on designing specialized hardware accelerators for applications including privacy preserving computation. His research is proving that the future of computing can be privacy-forward while making huge advances in information processing and hardware design.

"I’m incredibly excited to have won this award, said Reagen. "The grant will enable students to develop cutting-edge hardware accelerators to provide the computational horsepower necessary to speedup these emerging computational paradigms. In addition, we’ll be able to expand our research scope beyond hardware and construct compilers to automatically translate plaintext programs to the privacy-preserving representations. By overcoming the programming and hardware performance challenges we can facilitate a seamless transition to private computing!"

Whether it’s personal messages, health data, financial transactions, or confidential business communications, encryption plays a pivotal role in maintaining privacy and ensuring the integrity of our digital interactions. Typically, data encryption protects data in transit: it’s locked in an encrypted “container” for transit over potentially unsecured networks, then unlocked at the other end, by the other party for analysis. But outsourcing to a third-party is inherently insecure.

Reagen’s work focuses on building the hardware and software necessary to do all of your computer work — from basic apps to complicated algorithms — fully encrypted, from beginning to end.

Privacy-preserving computation, a cutting-edge computational paradigm, allows for computations on encrypted data without compromising privacy. Currently, its widespread adoption is hindered by its high computational costs, rendering it impractical. Previous studies have consistently shown that programs utilizing privacy-preserving computation are significantly slower, by orders of magnitude, compared to traditional methods. 

This funding will support Reagen’s aims to revolutionize privacy-preserving computation by introducing novel hardware and software techniques to enhance its processing speed. These advancements will bring privacy-preserving computation to a practical level, ensuring users unparalleled privacy guarantees while maintaining access to essential online services. 

To overcome the significant slowdown, optimizations across the computational stack are essential. This project employs a co-design approach, considering the intricate interplay between hardware, software, and algorithms. A crucial insight is that privacy-preserving computation inherently operates in a data-oblivious manner, meaning that all program behaviors are known statically during compilation. Leveraging this characteristic, careful coordination between hardware and software can achieve the drastic speedups necessary for practical implementation. 

The project focuses on two types of privacy-preserving computation: arithmetic (e.g., homomorphic encryption) and Boolean (e.g., garbled circuits). For homomorphic encryption, the project explores systolic array-based architectures and dataflow optimizations to accelerate computation. Additionally, methods to expedite Boolean computations are being developed, including a chiplet-based architecture to enhance scalability and program partitioning algorithms for efficient workload distribution across chiplets. 

Finally, the project addresses the challenge of efficiently mapping plaintext programs to privacy-preserving computation primitives through compiler infrastructure development. The outcomes of this project will establish the groundwork for processing in the era of private computing.

Additionally, the project will develop educational materials to facilitate the integration of this paradigm into various educational levels, from K-12 programs to university classrooms and conference tutorials.

“Brandon Reagen is working at the cutting-edge of cybersecurity and computing, and this award recognizes the enormous potential of his research,” said NYU Tandon Dean Jelena Kovačević. “The advancement of privacy-preserving computation will have profound implications for security, healthcare, sustainability, and scientific research, and I am thrilled to see this technology being pioneered at our school.”

Reagen — who earned a doctoral degree in computer science from Harvard in 2018 and undergraduate degrees in computer systems engineering and applied mathematics from the University of Massachusetts, Amherst, in 2012 — focused on creating specialized hardware accelerators for applications like deep learning. These accelerators enhance specialized hardware that can be made orders of magnitude more efficient than general-purpose platforms like CPUs. Enabling accelerators requires changes to the entire compute stack, and to bring about this change, he has made several contributions to lowering the barrier of using accelerators as general architectural constructs, including benchmarking, simulation infrastructure, and System on a Chip (SoC) design.

Before coming to NYU Tandon, Reagen was a former research scientist on Facebook’s AI Infrastructure Research team, where he became deeply involved in studying privacy. This combination of a deep cutting-edge computer hardware background and a commitment to digital security made him a perfect fit for NYU Tandon and the NYU Center for Cybersecurity, which has been at the forefront of cybersecurity research since its inception.