Junzheng Shi

Junzheng Shi

Auto-generated profile, based on publicly available information

Junzheng Shi

Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 February 2026 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
YSYangguang Shao
Yangguang Shao
JYJiahao Yu
Jiahao Yu
HMHanwen Miao
Hanwen Miao
GGGaopeng Gou
Gaopeng Gou
ZLZhen Li
Zhen Li
JSJunzheng Shi
Junzheng Shi
Large Language Models (LLMs) have gained widespread use in various applications due to their powerful capability to generate human-like text. However, prompt injection attacks, which involve overwriting a model’s original instructions with malicious prompts to manipulate the generated text, have raised significant concerns about the security and reliability of LLMs. In this paper, we propose PromptFuzz, a novel testing framework that leverages fuzzing techniques to systematically assess the robustness of LLMs against prompt injection attacks. Inspired by software fuzzing, PromptFuzz selects promising seed prompts and generates a diverse set of prompt injections to evaluate the target LLM’s resilience. PromptFuzz operates in two stages: the prepare phase, which involves selecting promising initial seeds and collecting few-shot examples, and the focus phase, which uses the collected examples to generate diverse, high-quality prompt injections. By deploying the generated attack prompts from PromptFuzz in a real-world competition, we achieved the 7th ranking out of over 4000 participants (top 0.14%) within 2 hours, demonstrating PromptFuzz’s effectiveness compared to experienced human attackers. Additionally, we also deploy the generated attack prompts on 50 popular LLM-integrated online applications, including those from Coze and OpenAI, and found that 92% of them can be exploited by PromptFuzz. We also run PromptFuzz on 15 online LLM-based resume judging applications and found that 13 of these applications’ responses can be hijacked by PromptFuzz.

27 November 2025 in Computers & Security
Verified
Journal Article
Closed access
MCMengrui Cao
Mengrui Cao
GGGaopeng Gou
Gaopeng Gou
JSJunzheng Shi
Junzheng Shi
GXGang Xiong
Gang Xiong
ZLZhen Li
Zhen Li
JLJiayu Li
Jiayu Li

27 October 2025
Verified
Conference Paper
Open access
YLYili Li
Yili Li
GXGang Xiong
Gang Xiong
GGGaopeng Gou
Gaopeng Gou
XQXiangyan Qu
Xiangyan Qu
JZJiamin Zhuang
Jiamin Zhuang
JSJunzheng Shi
Junzheng Shi