PeopleofSuperintelligence

Researcher

Guoxing Chen

Also known as 陈国兴

Guoxing Chen is a computer security researcher at Shanghai Jiao Tong University whose work on trusted execution environments extends to the security of machine-learning models. He earned bachelor's and master's degrees at SJTU in 2010 and 2013 and a PhD at the Ohio State University in 2019. At Ohio State he coauthored the SgxPectre attacks on Intel SGX enclaves, and he worked as a research scientist at Facebook before joining the SJTU faculty in 2021. His later papers include a 2022 method for fingerprinting stolen deep neural networks and 2025 studies of trojaned LLM adapters and of inverting LLM internal states. He is a tenure-track associate professor in SJTU's School of Computer Science and a member of its Institute of Artificial Intelligence and Cognitive Security.

Badges

Timeline

  1. 2010–2019

    Degrees from SJTU and Ohio State

    He earns a bachelor's degree at Shanghai Jiao Tong University in 2010 and a master's degree there in 2013. He completes a PhD at the Ohio State University in 2019, advised by Ten H. Lai, Dong Xuan and Yinqian Zhang.

  2. 2018

    HyperRace for SGX enclaves

    In 2018, he coauthors "Racing in Hyperspace" at the IEEE Symposium on Security and Privacy. The paper presents HyperRace, an LLVM-based tool that instruments SGX enclave programs, creates a shadow thread for each enclave thread and asks the operating system to place both on the same physical core, which closes Hyper-Threading side channels.

  3. 2018–2020

    The SgxPectre attacks

    In 2018, while at Ohio State, he posts SgxPectre on arXiv with Sanchuan Chen, Yuan Xiao, Yinqian Zhang, Zhiqiang Lin and Ten H. Lai. The attacks use speculative execution to steal seal keys and attestation keys from Intel signed quoting enclaves. The work appears at IEEE EuroS&P in 2019 and in IEEE Security & Privacy in 2020.

  4. 2019–2021

    Research scientist at Facebook

    He works as a research scientist at Facebook from 2019 until he moves to Shanghai Jiao Tong University in March 2021.

  5. 2021–2024

    Assistant professor at SJTU

    In March 2021, he joins SJTU's School of Computer Science, where he is a tenure-track assistant professor through 2024.

  6. 2022

    Fingerprinting stolen neural networks

    In 2022, he coauthors a CVPR oral paper on fingerprinting deep neural networks with universal adversarial perturbations. The method lets a service provider verify whether a suspect model was stolen through model extraction attacks, detecting model IP breaches with confidence above 99.99 within 20 fingerprints.

  7. 2025

    Trojan adapters and prompt inversion

    In 2025, he coauthors two papers on attacks against large language models. "The Philosopher's Stone" at NDSS shows that an infected low-rank adapter can make an LLM output adversary-defined content on specific triggers, and "Depth Gives a False Sense of Privacy" at USENIX Security shows that LLM internal states can be inverted to recover input prompts, including a 4,112-token medical consulting prompt.

  8. Since 2025

    Associate professor at SJTU

    In 2025, he becomes a tenure-track associate professor at SJTU's School of Computer Science, where he is a member of the Institute of Artificial Intelligence and Cognitive Security. His team takes students in system security, hardware security, side channels, data privacy and trusted execution environments.

Career

  1. Since 2021Shanghai Jiao Tong UniversityAssistant professor, Associate professor
  2. 2019–2021MetaResearch scientist

Education

  1. 2019Ohio State UniversityPhD
  2. 2013Shanghai Jiao Tong UniversityMaster's degree
  3. 2010Shanghai Jiao Tong UniversityBachelor's degree

From the biography.

  1. 23% of people shaping AI who left a university for a company later returned to a universityIncludes Guoxing Chen. We estimate that 468 of the 2,011 people shaping AI who left a university for a company (23%) later returned to a university after a median of 5 years, and 163 of 829 (20%) made the reverse round trip.
  2. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorateIncludes Shanghai Jiao Tong University. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorate. Across 2,116 people with both an undergraduate degree and a doctorate recorded, we trace which undergraduate schools feed which doctoral programs, how often students stay at the same school, and how paths differ by birth-country region.
  3. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Shanghai Jiao Tong University. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Shanghai Jiao Tong 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 with dated positions at the same organization in the same years.

Sources and credits

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

  1. Guoxing Chen's Homepage donnod.github.io. Checked 21 October 2026.
  2. Guoxing Chen-上海交通大学计算机学院（网络空间安全学院、密码学院） cs.sjtu.edu.cn. Checked 21 October 2026.
  3. Racing in Hyperspace: Closing Hyper-Threading Side Channels on SGX with Contrived Data Races | NSF Public Access Repository par.nsf.gov. Checked 21 October 2026.
  4. SgxPectre Attacks: Stealing Intel Secrets from SGX Enclaves via Speculative Execution arxiv.org. Checked 21 October 2026.
  5. Spectre haunts Intel's SGX defense: CPU flaws can be exploited to snoop on enclaves theregister.com. Checked 21 October 2026.
  6. Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations arxiv.org. Checked 21 October 2026.
  7. The Philosopher's Stone: Trojaning Plugins of Large Language Models arxiv.org. Checked 21 October 2026.
  8. Depth Gives a False Sense of Privacy: LLM Internal States Inversion | USENIX usenix.org. Checked 21 October 2026.
  9. Institute of Artificial Intelligence and Cognitive Security-上海交通大学计算机学院（网络空间安全学院、密码学院） cs.sjtu.edu.cn. Checked 21 October 2026.