PeopleofSuperintelligence

Researcher

Ho Chen

Also known as Hao Chen

Ho Chen is a computer security researcher who applies machine learning to software security and studies the security of AI systems. He earned his PhD at UC Berkeley in 2004 under David Wagner, won a US National Science Foundation CAREER award in 2007, and proposed the MagNet defense against adversarial examples with Dongyu Meng in 2017. With Peng Chen, he presented the Angora fuzzer at the IEEE Symposium on Security and Privacy in 2018, and by 2019 he led the security research group at ByteDance's AI lab while on academic leave from UC Davis. He joined the University of Hong Kong as a Chair Professor in 2024, and today he is Deputy Director of its Musketeers Foundation Institute of Data Science, directs the JC STEM Lab of Intelligent Cybersecurity, and is an IEEE fellow.

Timeline

  1. 2004

    A Berkeley PhD and MOPS

    A PhD from the Computer Science Division at the University of California, Berkeley comes in 2004, with David Wagner as his dissertation adviser. He is best known for MOPS, a tool that finds security vulnerabilities in C programs.

  2. 2007–2010

    NSF CAREER and a UC Davis award

    In 2007 he wins the US National Science Foundation CAREER award, and in 2010 the College of Engineering Faculty Award at the University of California, Davis, where he works in the Department of Computer Science.

  3. 2017

    MagNet against adversarial examples

    With Dongyu Meng, he proposes MagNet in 2017, a framework that defends neural network classifiers against adversarial examples using separate detector networks and a reformer network. It appears at the ACM Conference on Computer and Communications Security (CCS) 2017.

  4. 2018

    The Angora fuzzer

    In 2018 he and Peng Chen present Angora at the IEEE Symposium on Security and Privacy, a mutation-based fuzzer that raises branch coverage by solving path constraints without symbolic execution. Angora finds 6, 52, 29, 40 and 48 new bugs in file, jhead, nm, objdump and size, respectively.

  5. By 2019

    Security group at ByteDance AI Lab

    By 2019 he is on academic leave from UC Davis and leads the security research group at ByteDance's AI lab. His fuzzing work by then includes Angora (S&P 2018) and Matryoshka (CCS 2019).

  6. January 2024

    Guest seminar at HKU

    Under the name Hao Chen, he gives an HKU Institute of Data Science guest seminar in January 2024, "AI-driven Software Security", as a professor of computer science at UC Davis. He shows how to turn fuzz testing into a principled approach based on machine learning and how to use fuzz testing to improve program understanding.

  7. August 2024

    Chair Professor at HKU

    In August 2024 the HKU Musketeers Foundation Institute of Data Science welcomes him as a Chair Professor and HKU-100 Scholar, jointly appointed by the Institute and the Department of Computer Science. He directs the JC STEM Lab of Intelligent Cybersecurity.

  8. As of October 2026

    Deputy Director at HKU IDS

    He is Deputy Director of the HKU Musketeers Foundation Institute of Data Science and Chair Professor of Cybersecurity in the Department of Computer Science. His work covers AI-driven security and the security of AI, including fuzzing and the robustness of machine learning models, and he is an IEEE fellow.

Career

  1. Since 2024University of Hong KongChair Professor of Cybersecurity
  2. University of California, DavisProfessor of Computer Science
  3. ByteDanceSecurity research group lead

Education

  1. 2004University of California, BerkeleyPhD

From the biography.

  1. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes University of Hong Kong. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  2. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes University of Hong Kong. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  3. Google has the highest combined h-index among AI organizationsIncludes University of Hong Kong. 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.
  4. 5 of the 25 people with the most-cited recent papers also lead on career citationsIncludes University of Hong Kong. We compare citations to 2023–2025 papers with career citations and h-index, after correcting reviewed publication-date errors: who leads, when they started and where they work.

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 Ho Chen yet. Send us a free-licensed photo.

  1. Hao Chen cs.ucdavis.edu. Checked 21 October 2026.
  2. Chen, Hao – Computer Science faculty.engineering.ucdavis.edu. Checked 21 October 2026.
  3. [1705.09064] MagNet: a Two-Pronged Defense against Adversarial Examples arxiv.org. Checked 21 October 2026.
  4. Chen, Ho cs.hku.hk. Checked 21 October 2026.
  5. [1803.01307] Angora: Efficient Fuzzing by Principled Search arxiv.org. Checked 21 October 2026.
  6. Oct 24 - Talk: Principled fuzzing driven by mathematics (Prof. Hao Chen) cs.pku.edu.cn. Checked 21 October 2026.
  7. IDS Guest Seminar: AI-driven Software Security - HKU Musketeers Foundation Institute of Data Science datascience.hku.hk. Checked 21 October 2026.
  8. Welcoming Professor Ho CHEN, Chair Professor, on board in HKU IDS! datascience.hku.hk. Checked 21 October 2026.
  9. Ho CHEN - HKU Musketeers Foundation Institute of Data Science datascience.hku.hk. Checked 21 October 2026.