Junzheng Shi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Junzheng Shi has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Gang Xiong
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
2 shared publications - Gaopeng Gou
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China
2 shared publications - Zhen Li
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
2 shared publications Gaopeng Gou
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
1 shared publicationHanwen Miao
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
1 shared publication- Jiahao Yu
Northwestern University, Evanston, USA
1 shared publication
Latest Publications
- Top Cited Papers
- 23 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 2727-2741
PromptFuzz: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs
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.
- 23 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 2727-2741
Top Cited PapersPromptFuzz: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs
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
- Published by Elsevier in Computers & Security
- Vol. 162
MDDB-AETB: Malicious domain detection boosting based on alignment with encrypted traffic behavior in restricted scenarios
- 27 November 2025
- Published by Elsevier in Computers & Security
- Vol. 162
MDDB-AETB: Malicious domain detection boosting based on alignment with encrypted traffic behavior in restricted scenarios
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4001-4009
T2VParser: Adaptive Decomposition Tokens for Partial Alignment in Text to Video Retrieval
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4001-4009
Open AccessT2VParser: Adaptive Decomposition Tokens for Partial Alignment in Text to Video Retrieval