Zhen Sun

Hello! I'm a PhD candidate in Data Science and Analytics at The Hong Kong University of Science and Technology (Guangzhou). I am advised by Prof. Xinlei He, with primary supervision from Prof. Jiaheng Wei and co-supervision from Prof. Yutao Yue at HKUST(GZ).

My research interests lie in Trustworthy AI, specifically focusing on the following directions:

Security & Privacy

Studying backdoors, jailbreaks, and privacy risks in modern AI models.

Content Moderation

Detecting and moderating harmful, deceptive, and AI-generated content.

AI Application

Applying AI to enhance model capabilities and practical utility.

News

[2026.06] I passed the PhD Qualifying Examination at HKUST(GZ).
[2026.01] JALMBench was accepted at ICLR 2026.
[2025.12] I received First Prize in the Offline Testing Algorithm Competition of the 2025 China Intelligent Vehicle Future Challenge.
[2025.12] 6DAttack was accepted at AAAI 2026 as an Oral presentation.
[2025.12] I received the 2025 DSA Excellent Research Award.
[2025.09] FC-Attack was accepted at EMNLP 2025 Findings.
[2025.09] CHASM was accepted at NeurIPS 2025.
[2025.06] Unsafe LLM-Based Search was accepted at USENIX Security 2025.
[2025.05] AIGT on Social Media was accepted at ACL 2025, and MGT Generalization plus TH-Bench were accepted at KDD 2025.
[2025.03] PEFTGuard was accepted at IEEE S&P 2025.

[2024.11] AdSpectorX received the Best Paper Award at SENSYS-SocialMeta 2024.
[2024.06] I received my firm PhD offer from HKUST(GZ).

Selected Papers

^* denotes equal contribution. ^† denotes corresponding author. The complete list can be found at Google Scholar.

2025IEEE S&P

PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning

Zhen Sun, Tianshuo Cong, Yule Liu, Chenhao Lin, Xinlei He, Rongmao Chen, Xingshuo Han, Xinyi Huang.

2025ACL

Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media

Zhen Sun^*, Zongmin Zhang^*, Xinyue Shen, Ziyi Zhang, Yule Liu, Michael Backes, Yang Zhang, Xinlei He.

2025EMNLP Findings

FC-Attack: Jailbreaking Large Vision-Language Models via Auto-Generated Flowcharts

Ziyi Zhang^*, Zhen Sun^*, Zongmin Zhang, Jihui Guo, Xinlei He.

2026ICLR

JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models

Zifan Peng, Yule Liu, Zhen Sun, Mingchen Li, Zeren Luo, Jingyi Zheng, Wenhan Dong, Xinlei He, Xuechao Wang, Yingjie Xue, Shengmin Xu, Xinyi Huang.

2025USENIX Security

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search

Zeren Luo, Zifan Peng, Yule Liu, Zhen Sun, Mingchen Li, Jingyi Zheng, Xinlei He.

2025NeurIPS

CHASM: Unveiling Covert Advertisements on Chinese Social Media

Jingyi Zheng, Tianyi Hu, Yule Liu, Zhen Sun, Zongmin Zhang, Zifan Peng, Wenhan Dong, Xinlei He.

2026AAAI · Oral

6DAttack: Backdoor Attacks in the 6DoF Pose Estimation

Jihui Guo, Zongmin Zhang, Zhen Sun, Yuhao Yang, Jinlin Wu, Fu Zhang, Xinlei He.

2025KDD

TH-Bench: Evaluating Evading Attacks via Humanizing AI Text on Machine-Generated Text Detectors

Jingyi Zheng, Junfeng Wang, Zhen Sun, Wenhan Dong, Yule Liu, Xinlei He.

2025KDD

On the Generalization and Adaptation Ability of Machine-Generated Text Detectors in Academic Writing

Yule Liu, Zhiyuan Zhong, Yifan Liao, Zhen Sun, Jingyi Zheng, Jiaheng Wei, Qingyuan Gong, Fenghua Tong, Yang Chen, Yang Zhang, Xinlei He.

Services

Program Committee
- 2026 ACL ARR, AAAI, ACM MM
- 2025 AAAI, ACM MM, WWW (Web for Good)
Journal Reviewers: IEEE TDSC, IEEE TIFS, ACM TOPS, IJHCI

Selected Awards & Honors

First Prize, Offline Testing Algorithm Competition, 2025 China Intelligent Vehicle Future Challenge, 2025
DSA Excellent Research Award, 2025
Best Paper Award, SENSYS-SocialMeta 2024
Kaggle Competitions Expert (Vincent Sirius)
BUPT Third-class Scholarship & Excellent Student Leader, 2019 / 2020 / 2021