About me

Hi! I’m a tenure-track Assistant Professor at the University of Louisville CSE. I received my Ph.D. in Computer Science from the University of Kansas, advised by Dr. Bo Luo and Dr. Fengjun Li in 2024, and my Bachelor’s degree in Math from Wuhan University in 2019. My research interests are within the broad areas of Cybersecurity and AI, including adversarial and privacy-preserving machine learning, AI SAFE-T (Safety, Accountability, Fairness, Explainability, and Transparency), AI for Cybersecurity, and so on.

I am looking for self-motivated students to join my group. Please contact me at {julianzy2024 AT gmail DOT com} if you are interested!

News

  • Jun 2024. Our paper “The Adversarial AI-Art: Understanding, Generation, Detection, and Benchmarking” has been accepted to ESORICS 2024. Congrats to Yuying!
  • May 2024. Our CCS artifact (Zenodo) of “On the Detectability of ChatGPT Content” is granted Artifacts Available, Artifacts Evaluated, and Results Reproduced Badges. Thanks to our Reviewers!
  • May 2024. Our paper “The Invisible Polyjuice Potion: an Effective Physical Adversarial Attack against Face Recognition” has been accepted to ACM CCS 2024. Congrats to Ye!
  • Apr 2024. Our paper “On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing” has been accepted to ACM CCS 2024.
  • Mar 2024. Our paper “PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption” has been accepted to PETS 2024. Congrats to Liangqin!
  • Sep 2023. Our paper “Certificate Transparency Revisited: The Public Inspections on Third-party Monitors” has been accepted to NDSS 2024. Congrats to Aozhuo!
  • June 2023. Our preprint “Check Me If You Can: Detecting ChatGPT-Generated Academic Writing using CheckGPT” is available. [Github][Huggingface]
  • Apr 2023. I will join Visa Inc. this summer as a PhD Research Scientist Intern working on AI and Cybersecurity.
  • Aug 2022. Our paper “LoneNeuron: a Highly-effective Feature-domain Neural Trojan using Invisible and Polymorphic Watermark” has been accepted to ACM CCS 2022.
  • July 2022. Our paper “Hide and Seek: on the Stealthiness of Attacks against Deep Learning Systems” has been accepted to ESORICS 2022.