PeopleofSuperintelligence

Researcher

Ninghui Li

Ninghui Li is a computer scientist who works on data privacy and security and now directs AI security research at Perplexity. After a bachelor's degree at the University of Science and Technology of China in 1993 and a PhD at New York University in 2000, he was a research associate at Stanford from 2000 to 2003 and joined Purdue's computer science faculty in 2003. His 2007 paper on t-closeness, written with Tiancheng Li and Suresh Venkatasubramanian, received the ICDE 2017 Influential Paper award, and in 2016 he co-wrote the book Differential Privacy: From Theory to Practice. He chaired ACM SIGSAC from 2017 to 2021 and became a Fellow of both the ACM and the IEEE in 2021, and in 2026 he co-authored work on membership inference attacks against diffusion language models. Since February 2026, he is the inaugural director of Perplexity's Secure Intelligence Institute while on part-time research leave from Purdue, where he is a professor of computer science.

Badges

Timeline

  1. 1993–2003

    From USTC to Purdue

    He earns a bachelor's degree in computer science from the University of Science and Technology of China in 1993 and a PhD in computer science from New York University in 2000. From 2000 to 2003 he is a research associate in Stanford University's Computer Science Department, and in 2003 he joins the computer science faculty at Purdue University.

  2. 2007–2017

    The t-closeness paper

    In 2007, with Tiancheng Li and Suresh Venkatasubramanian, he publishes "t-Closeness: Privacy Beyond k-Anonymity and l-Diversity" at ICDE. The paper asks that the distribution of a sensitive attribute in each group of records stays within a threshold t of its distribution in the whole table, and it receives the ICDE 2017 Influential Paper award.

  3. 2016

    A book on differential privacy

    Together with Min Lyu, Dong Su and Weining Yang, he publishes Differential Privacy: From Theory to Practice in 2016, in the Synthesis Lectures on Information Security, Privacy, & Trust from Morgan & Claypool.

  4. 2017–2024

    SIGSAC chair and TOPS editor

    He chairs ACM's Special Interest Group on Security, Audit and Control (SIGSAC) from 2017 to 2021. From 2020 to 2024 he is Editor-in-Chief of ACM Transactions on Privacy and Security (TOPS).

  5. 2021–2022

    Fellow of ACM and IEEE

    ACM names him a Fellow in 2021 for contributions to data privacy, access control, and trust management, and the IEEE elevates him to Fellow in 2021 for contributions to data privacy and security. In 2022 he receives the ACM SIGSAC Outstanding Contributions Award.

  6. 2023

    The ACTION AI institute

    He takes part in ACTION, the NSF-funded AI Institute for Agent-based Cyber Threat Intelligence and Operation, from its start in 2023; the funding period runs to 2028.

  7. 2026

    Membership inference and agent security

    In 2026 he coauthors an ICLR paper that presents the first systematic investigation of membership inference attacks on diffusion language models and introduces SAMA, which improves AUC by 30% relative to the best baseline across nine datasets. In March 2026 he also coauthors "Security Considerations for Artificial Intelligence Agents" with Kaiyuan Zhang, Kyle Polley and Jerry Ma, on the security of frontier AI agents.

  8. Since February 2026

    Directing Perplexity's Secure Intelligence Institute

    In February 2026 he joins Perplexity AI on a part-time research leave from Purdue, and he becomes the inaugural director of its Secure Intelligence Institute, launched in March 2026 as a research center for security, privacy, and trust in frontier AI. The institute's research covers authentication, usable privacy and security, robust machine learning, and the defense of agentic AI systems. He holds an appointment as the Samuel D. Conte Professor of Computer Science at Purdue, where he is also Associate Department Head.

Career

  1. Since 2026PerplexityInaugural Director
  2. Since 2003Purdue UniversityProfessor of Computer Science; Associate Department Head
  3. 2000–2003Stanford UniversityResearch Associate

Education

  1. 2000New York UniversityPhD
  2. 1993University of Science and Technology of ChinaBachelor's degree

From the biography.

  1. Among employers with 30+ full-time cases, OpenAI leads primary technical role H-1B pay at $310,000, and Amazon, Google and Microsoft file 57% of all casesIncludes Perplexity. Across 440,669 certified US H-1B filings from 44 employers (FY2020–FY2026), OpenAI leads primary technical role base pay at $310,000 and xAI leads overall base pay at $290,000.
  2. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Perplexity. 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.
  3. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes Stanford University. 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.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Purdue University. 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.

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 Ninghui Li yet. Send us a free-licensed photo.

  1. Ninghui Li - Department of Computer Science - Purdue University cs.purdue.edu. Checked 22 October 2026.
  2. t-closeness - Wikipedia en.wikipedia.org. Checked 22 October 2026.
  3. Ninghui Li Named ACM Fellow - CERIAS - Purdue University cerias.purdue.edu. Checked 22 October 2026.
  4. Li Named 2021 IEEE Fellow - Department of Computer Science - Purdue University cs.purdue.edu. Checked 22 October 2026.
  5. CERIAS faculty singled out for cybersecurity honors - Office of Research research.purdue.edu. Checked 22 October 2026.
  6. Ninghui Li to serve as Secure Intelligence Institute Inaugural Director | The ACTION Institute action.ucsb.edu. Checked 22 October 2026.
  7. Ninghui Li's Homepage cs.purdue.edu. Checked 22 October 2026.
  8. [2601.20125] Membership Inference Attacks Against Fine-tuned Diffusion Language Models arxiv.org. Checked 22 October 2026.
  9. [2603.12230] Security Considerations for Artificial Intelligence Agents arxiv.org. Checked 22 October 2026.
  10. Announcing the Secure Intelligence Institute perplexity.ai. Checked 22 October 2026.
  11. Secure Intelligence Institute perplexity.ai. Checked 22 October 2026.