PeopleofSuperintelligence

Researcher

Edward Suh

Also known as G. Edward Suh

Edward Suh is a computer systems researcher whose work connects hardware security with AI privacy and language-model memorization. After earning degrees at Seoul National University and MIT, he developed the AEGIS secure processor in 2003, published 2004 papers on physical unclonable functions and dynamic information flow tracking, and served on Cornell University's electrical and computer engineering faculty from 2007 to 2023. His physical unclonable function work was adopted in commercial Xilinx FPGAs for secret-key storage, IEEE named him a Fellow in 2019, and Intel gave his AEGIS work a Hardware Security Test of Time Award in August 2022 while he was a Research Scientist in Meta's FAIR team. In 2026, his coauthored paper estimating GPT-style language model capacity at 3.6 bits per parameter received an ICML Outstanding Paper Honorable Mention. As of October 2026, he is a Senior Director of Research at NVIDIA, where he leads a security and privacy research group, and serves as an adjunct professor at Cornell.

Timeline

  1. 2003

    The AEGIS secure processor

    In 2003, he develops the AEGIS secure processor design, showing that hardware can protect the integrity and confidentiality of critical software without trusting an operating system.

  2. 2004

    Physical unclonable functions

    At the 2004 Symposium on VLSI Circuits, he publishes a paper on physical unclonable functions that later wins the symposium's most frequently cited paper award for its 30th anniversary. His PUF work is used in commercial products such as Xilinx FPGAs for storing secret keys.

  3. 2004

    Dynamic information flow tracking

    He publishes a paper on dynamic information flow tracking (DIFT) at the 2004 International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), which later receives the conference's most influential paper award.

  4. 2007–2023

    Cornell ECE faculty

    After earning a B.S. in electrical engineering from Seoul National University and an M.S. and Ph.D. in electrical engineering and computer science from MIT, he joins Cornell University's School of Electrical and Computer Engineering faculty in 2007 and serves there through 2023.

  5. 2019

    Named an IEEE Fellow

    In 2019, the IEEE Board of Directors names him an IEEE Fellow for contributions to the development of secure hardware circuits and processors.

  6. August 2022

    Meta FAIR and test-of-time award

    Before joining NVIDIA, he works as a Research Scientist in Meta's Fundamental AI Research (FAIR) team. In August 2022, while serving as a Cornell professor and Meta AI research scientist, he receives an Intel Hardware Security Test of Time Award for his AEGIS secure processor work and its contribution to trusted execution environments.

  7. 2026

    ICML paper on memorization

    In 2026, Suh coauthors “How much can language models memorize?” with John Xavier Morris, Chawin Sitawarin, Narine Kokhlikyan, Chuan Guo, Alexander M. Rush, Kamalika Chaudhuri and Saeed Mahloujifar. Their measurements estimate that GPT-style models have a capacity of approximately 3.6 bits per parameter, and ICML gives the paper an Outstanding Paper Honorable Mention in July 2026.

  8. As of October 2026

    NVIDIA security and privacy research

    As of October 2026, Suh is a Senior Director of Research at NVIDIA, where he leads a group in security and privacy research focused on building secure computing systems for secure and private AI and using AI to improve computer system security. He also serves as an adjunct professor in the School of Electrical and Computer Engineering at Cornell University.

Career

  1. NowCornell UniversityAdjunct Professor
  2. NowNVIDIASenior Director of Research
  3. FAIR (Meta)Research Scientist

Education

  1. Seoul National UniversityB.S.
  2. Massachusetts Institute of TechnologyM.S.

From the biography.

  1. Google has the highest combined h-index among AI organizationsIncludes NVIDIA. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.
  2. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes NVIDIA. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.
  3. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes NVIDIA. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.
  4. 11% of AI doctorate holders from 2010 to 2016 founded or led a company or lab by 10 years after graduationIncludes Cornell University. We estimate how often AI doctorate holders founded or led a company or lab by 10 years after graduation, how waiting times compare between founders and top jobs, and which universities trained the most.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Edward Suh yet. Send us a free-licensed photo.

  1. G. Edward Suh – Suh Research Group tsg.ece.cornell.edu. Checked 22 October 2026.
  2. Edward Suh | Research research.nvidia.com. Checked 22 October 2026.
  3. Author: G. Edward Suh | NVIDIA Technical Blog developer.nvidia.com. Checked 22 October 2026.
  4. IEEE Fellow – Suh Research Group tsg.ece.cornell.edu. Checked 22 October 2026.
  5. CSL Professor Edward Suh Named IEEE Fellow – Computer Systems Laboratory sites.coecis.cornell.edu. Checked 22 October 2026.
  6. Intel Names Hardware Security Award Winners intc.com. Checked 22 October 2026.
  7. How much can language models memorize? proceedings.mlr.press. Checked 22 October 2026.
  8. Announcing the ICML 2026 Awards – ICML Blog blog.icml.cc. Checked 22 October 2026.