Zhengyuan Jiang

I am a fourth-year Ph.D. student in the Electrical and Computer Engineering Department at Duke University, advised by Prof. Neil Gong. I received my B.Eng. from the University of Science and Technology of China (USTC) in 2022. In summer 2021, I worked with Prof. Yu Li at The Chinese University of Hong Kong (CUHK). I am currently a research scientist intern at ByteDance, focusing on multimodal LLM and AI agent security. I am open to research collaborations—if these directions resonate with you, please feel free to reach out~

Email / Google Scholar / GitHub / Twitter / LinkedIn

News

Apr, 2026. “Benchmarking Vision-Language Models under Contradictory Virtual Content Attacks in Augmented Reality” is accepted by CVPR 2026 (Findings)! Dataset: GitHub.
Apr, 2026. “Fingerprinting LLMs via Prompt Injection” is accepted by ACL 2026 (Main)!
Jan, 2026. “Watermark-based Attribution of AI-Generated Content” is accepted by ICLR 2026!
Jan, 2026. “Jailbreaking Safeguarded Text-to-Image Models via Large Language Models” is accepted by EACL 2026 (Findings)!
Jan, 2025. “A Transfer Attack to Image Watermarks” is accepted by ICLR 2025!
Sep, 2024. “AudioMarkBench: Benchmarking Robustness of Audio Watermarking” is accepted by NeurIPS DB Track 2024! Code is available on GitHub!
Jul, 2024. “Certifiably Robust Image Watermark” is accepted by ECCV 2024! Code is available on GitHub!
Sep, 2023. “Evading Watermark based Detection of AI-Generated Content” is accepted by CCS 2023!
May, 2023. “Evading Watermark based Detection of AI-Generated Content” is available on arXiv and GitHub!
Jul, 2022. I received a B.Eng. from USTC, Information Science and Technology Elite Class!

Experience

ByteDance

Research Scientist Intern — multimodal LLM and AI agent security

May 2026 – Present

Duke University

Ph.D. student, Electrical & Computer Engineering

Aug 2022 – Present

Advised by Prof. Neil Gong

CUHK · Artificial Intelligence in Healthcare (AIH)

Research Intern

May 2021 – Nov 2021

Hosted by Prof. Yu Li

University of Science and Technology of China (USTC)

B.Eng., Information Science and Technology Elite Class

Sep 2018 – Jul 2022

Selected Publications

2026

Watermark-based Attribution of AI-Generated Content

Zhengyuan Jiang, Moyang Guo, Yuepeng Hu, Yupu Wang, Neil Zhenqiang Gong

International Conference on Learning Representations (ICLR), 2026.

[PDF]

Jailbreaking Safeguarded Text-to-Image Models via Large Language Models

Zhengyuan Jiang, Yuepeng Hu, Yuchen Yang, Yinzhi Cao, Neil Zhenqiang Gong

EACL (Findings), 2026.

[PDF]

Fingerprinting LLMs via Prompt Injection

Yuepeng Hu, Zhengyuan Jiang, Mengyuan Li, Osama Ahmed, Zhicong Huang, Cheng Hong, Neil Gong

ACL (Main), 2026.

[PDF]

Benchmarking Vision-Language Models under Contradictory Virtual Content Attacks in Augmented Reality

Yanming Xiu, Zhengyuan Jiang, Neil Zhenqiang Gong, Maria Gorlatova

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, 2026.

[PDF] [dataset]

2025

A Transfer Attack to Image Watermarks

Yuepeng Hu, Zhengyuan Jiang, Moyang Guo, Neil Zhenqiang Gong

International Conference on Learning Representations (ICLR), 2025.

[PDF]

2024

AudioMarkBench: Benchmarking Robustness of Audio Watermarking

Hongbin Liu, Moyang Guo, Zhengyuan Jiang, Lun Wang, Neil Zhenqiang Gong

NeurIPS Datasets and Benchmarks Track, 2024.

[PDF] [code]

Certifiably Robust Image Watermark

Zhengyuan Jiang, Moyang Guo, Yuepeng Hu, Jinyuan Jia, Neil Zhenqiang Gong

European Conference on Computer Vision (ECCV), 2024.

[PDF] [code]

2023

Evading Watermark based Detection of AI-Generated Content

Zhengyuan Jiang, Jinghuai Zhang, Neil Zhenqiang Gong

ACM Conference on Computer and Communications Security (CCS), 2023.

[PDF] [code]

IPCert: Provably Robust Intellectual Property Protection for Machine Learning

Zhengyuan Jiang, Minghong Fang, Neil Zhenqiang Gong

International Conference on Computer Vision (ICCV) Workshop, 2023.

[PDF]

Preprints & reports

EditTrack: Detecting and Attributing AI-assisted Image Editing

Zhengyuan Jiang, Yuyang Zhang, Moyang Guo, Neil Zhenqiang Gong

arXiv preprint

[PDF]

Safetext: Safe Text-to-Image Models via Aligning the Text Encoder

Yuepeng Hu, Zhengyuan Jiang, Neil Zhenqiang Gong

arXiv preprint

[PDF]

Securing the Future of GenAI: Policy and Technology

Mihai Christodorescu, Ryan Craven, Soheil Feizi, Neil Gong, Mia Hoffmann, Somesh Jha, Zhengyuan Jiang, Mehrdad Saberi Kamarposhti, John Mitchell, Jessica Newman, Emelia Probasco, Yanjun Qi, Khawaja Shams, Matthew Turek

IACR ePrint, 2024

[PDF]

Academic service

Conference reviewer: ICLR 2026, 2025; CVPR 2026; AAAI 2026; NeurIPS 2025; ACM MM 2024, 2023.
ICML 2026: Gold Reviewer.