Publications

You can find the full list of publications on my
Google Scholar.

Cloud and Infrastructure Security

WILD Attack: Stealthy Undermining of Wi-Fi-Based Geolocation Through Remote Crowdsourced Data Injection
Changjia Zhu, Xiao Han, Parush Gera, Zhuo Lu, Tempestt Neal, Yao Liu
USENIX Security 2026

Understanding and Mitigating Infrastructure-Level Disruption in Wi-Fi Positioning Systems
Changjia Zhu, Xiao Han, Parush Gera, Mingkui Wei, Zhuo Lu, Tempestt Neal, Yao Liu
Under Review, IEEE Transactions on Dependable and Secure Computing, 2026

Shadow Hunting in the Cloud: Unearthing and Undermining the Target Application in a Vast Ocean of Servers
Changjia Zhu, Junjie Xiong, Zhuo Lu, Yao Liu
Under Review, 2026

Patent: Mitigating Infrastructure-Level Disruption in Wi-Fi Positioning Systems Changjia Zhu, Xiao Han, Parush Gera, Mingkui Wei, Zhuo Lu, Tempestt Neal, Yao Liu U.S. Patent Application (Submitted), 2026

LLM Security and Workflow Evaluation

Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models
Changjia Zhu, Junjie Xiong, Chong Zhang, Yongfeng Zhang, Yao Liu, Lingyao Li
EMNLP 2025 Findings

When Your Reviewer is an LLM: Biases, Divergence, and Prompt Injection Risks
Changjia Zhu, Junjie Xiong, Renkai Ma, Zhicong Lu, Zhuo Lu, Yao Liu, Lingyao Li
Under Review, Computers in Human Behavior, 2025

COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers
Junyu Wang, Changjia Zhu, Yuanbo Zhou, Lingyao Li, Xu He, Mingkui Wei, Junjie Xiong
Under Review, 2026

Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation
Changjia Zhu, Chi Zhang, Junjie Xiong, Xiaoran Xu, Lingyao Li, Yao Liu, Zhuo Lu
Under Review, ACM Transactions on Intelligent Systems and Technology

Large Language Models and Social Media Information Integrity: Opportunities, Challenges, and Research Directions
Junjie Xiong, Zhengyuan Jiang, Xiaoran Xu, Chi Zhang, Changjia Zhu, Ning Wang, Mingkui Wei, Zhuo Lu, Yao Liu, Lingyao Li
Under Revision, ACM Computing Surveys, 2025

Transformer Architecture and Guardrail Analysis

Prompt Overflow Attack: Bypassing LLM Safety Checkers via Overlength Prompting
Yuanbo Zhou, Changjia Zhu, Junyu Wang, Yan Zhai, Kun Sun, Xu He, Junjie Xiong
Under Review, 2026