PeopleofSuperintelligence

Researcher

Bo Li

Bo Li is a computer scientist whose research examines the trustworthiness of machine-learning systems. She earned a computer science PhD at Vanderbilt, worked with Dawn Song at UC Berkeley, and joined UIUC's faculty in 2018. Her work links robustness, privacy, and generalization; in 2022 she received the IJCAI Computers and Thought Award and first prize in VNN-COMP. She coauthored DecodingTrust, a NeurIPS 2023 Outstanding Paper that evaluated GPT-3.5 and GPT-4 across eight trustworthiness dimensions. She joined UChicago as an associate professor in July 2023 and led Virtue AI as CEO and co-founder; Meta hired her and her team for AI agent security in September 2026.

Photo of Bo Li

Timeline

  1. 2016–2018

    A PhD and a Berkeley postdoc

    She earned a PhD in computer science at Vanderbilt in 2016, then worked with Dawn Song as a postdoctoral researcher at UC Berkeley in 2017–2018. She joined UIUC's faculty in 2018.

  2. 2022

    An award for trustworthy AI

    Her work connects trustworthy machine learning with robustness, privacy, and generalization. In 2022, she received the IJCAI Computers and Thought Award and first prize in the International Verification Neural Networks Competition (VNN-COMP'22).

  3. July 2023

    Joining Chicago faculty

    She joined the University of Chicago's computer science faculty as an associate professor in July 2023, after an assistant professorship in computer science at UIUC.

  4. December 2023

    Testing GPT trustworthiness

    Her coauthored paper DecodingTrust won a NeurIPS 2023 Outstanding Paper Award in the benchmark category. It evaluates GPT-3.5 and GPT-4 across eight trustworthiness dimensions, including toxicity, bias, robustness, privacy, and fairness.

  5. By 2026

    Building Virtue AI

    She was CEO and co-founder of Virtue AI, which developed an AI-native security, governance, and compliance platform.

  6. As of October 2026

    Research and agent security

    She is a Research Associate Professor of Computer Science and Data Science at UChicago and an Abbasi Associate Professor at Illinois. In September 2026, Meta Superintelligence Labs hired Li and her Virtue AI team to bolster AI agent security.

Sources and credits

Photo: aisecure.github.io; AI Security (UIUC); creator not stated. License: Not stated by source. Source: aisecure.github.io. Cropped to a square and resized. Ask us to remove or replace this photo.

  1. Bo Li | CDS codas.uchicago.edu. Checked 14 October 2026.
  2. Bo Li | The Grainger College of Engineering | Illinois grainger.illinois.edu. Checked 14 October 2026.
  3. IJCAI Awards | IJCAI ijcai.org. Checked 14 October 2026.
  4. UChicago CS To Welcome Nine New Faculty Members Over the Next Two Academic Years – Department of Computer Science cs-www.uchicago.edu. Checked 14 October 2026.
  5. NeurIPS 2023 Award-winning paper by DSI Faculty Bo Li, DecodingTrust, provides a comprehensive framework for assessing trustworthiness of GPT models – Department of Computer Science cs.uchicago.edu. Checked 14 October 2026.
  6. Announcing the NeurIPS 2023 Paper Awards – NeurIPS Blog blog.neurips.cc. Checked 14 October 2026.
  7. Bo Li | Virtue AI virtueai.com. Checked 14 October 2026.
  8. Bo Li and her Virtue AI team hired by Meta | Siebel School of Computing and Data Science | Illinois siebelschool.illinois.edu. Checked 14 October 2026.