PeopleofSuperintelligence

Researcher

Chaowei Xiao

Chaowei Xiao researches AI security, with work on adversarial vision, autonomous driving, language models, and AI agents. He earned a bachelor's degree in software at Tsinghua and a PhD in computer science and engineering at Michigan, then held faculty roles at Arizona State and Wisconsin–Madison. His work includes spatially transformed adversarial examples, LiDAR spoofing research, and the Dolphins driving model. Schmidt Sciences named him a 2024 AI2050 Early Career Fellow. As of October 2026, he is an assistant professor at Johns Hopkins University and a researcher at NVIDIA Research, and he is visiting Stanford University.

Works
196
Citations
7,461
h-index
32

Publication numbers from OpenAlex, as of 15 October 2026.

Timeline

  1. 2015

    A software degree at Tsinghua

    He earns a bachelor's degree in the School of Software at Tsinghua University in 2015.

  2. 2018–2019

    Adversarial attacks on vision systems

    In 2018, he coauthors a paper that uses spatial transformations to create perceptually realistic adversarial examples that challenge existing defenses. In 2019, he coauthors a LiDAR spoofing study that evaluates two attack scenarios that may damage road safety and mobility.

  3. 2020

    A PhD from Michigan

    In 2020, he earns a PhD in computer science and engineering at the University of Michigan.

  4. 2021

    Assistant professor at ASU

    In 2021, he joins Arizona State University as an assistant professor of computer science and engineering after working at NVIDIA as a research scientist focused on machine learning robustness.

  5. October 2023

    Joining Wisconsin's iSchool

    In October 2023, he joins the University of Wisconsin–Madison iSchool as an assistant professor with work on machine learning security, privacy, and socially responsible systems.

  6. December 2023

    The Dolphins driving model

    In December 2023, he coauthors Dolphins, a vision-language model designed as a conversational driving assistant that processes video, text instructions, and historical control signals.

  7. 2024

    An AI2050 fellowship

    In 2024, Schmidt Sciences names him an AI2050 Early Career Fellow; his project focuses on red-teaming tools that discover and assess AI vulnerabilities.

  8. As of October 2026

    Assistant professor at Johns Hopkins

    As of October 2026, he is an assistant professor at Johns Hopkins University and a researcher at NVIDIA Research, and he is visiting Stanford University. His work focuses on security for language models and AI agents.

Sources and credits

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

  1. Chaowei Xiao | NVIDIA ASPIRE Group research.nvidia.com. Checked 15 October 2026.
  2. [1801.02612] Spatially Transformed Adversarial Examples arxiv.org. Checked 15 October 2026.
  3. [1907.06826] Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving arxiv.org. Checked 15 October 2026.
  4. Chaowei Xiao - 2021-2022 Fulton Schools New Faculty Member news.engineering.asu.edu. Checked 15 October 2026.
  5. iSchool Welcomes 4 New Faculty Members – The Information School – UW–Madison ischool.wisc.edu. Checked 15 October 2026.
  6. Dolphins: Multimodal Language Model for Driving | NVIDIA ASPIRE Group research.nvidia.com. Checked 15 October 2026.
  7. Chaowei Xiao - AI2050 ai2050.schmidtsciences.org. Checked 15 October 2026.
  8. Chaowei Xiao named AI2050 Early Career Fellow by Schmidt Sciences – The Information School – UW–Madison ischool.wisc.edu. Checked 15 October 2026.
  9. Chaowei Xiao · LLM & AI Agent Security · Johns Hopkins University xiaocw11.github.io. Checked 15 October 2026.