Jiahao Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiahao Yu has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Yangguang Shao
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
2 shared publications - Chengshang Hou
Chinese Academy of Sciences
1 shared publication - Chihao Shen
University of Maryland, College Park, MD, USA
1 shared publication - Chuanjiang Li
Department of Control Science and Engineering, Harbin Institute of Technology, Harbin, China
1 shared publication - Gang Xiong
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
1 shared publication Gaopeng Gou
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 992-1005
Locus: Agentic Predicate Synthesis for Directed Fuzzing
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 992-1005
Open AccessLocus: Agentic Predicate Synthesis for Directed Fuzzing
- 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.
- Open Access
POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models
Large language models (LLMs) have achieved remarkable success in various domains, primarily due to their strong capabilities in reasoning and generating human-like text. Despite their impressive performance, LLMs are susceptible to hallucinations, which can lead to incorrect or misleading outputs. This is primarily due to the lack of up-to-date knowledge or domain-specific information. Retrieval-augmented generation (RAG) is a promising approach to mitigate hallucinations by leveraging external knowledge sources. However, the security of RAG systems has not been thoroughly studied. In this paper, we study a poisoning attack on RAG systems named POISONCRAFT, which can mislead the model to refer to fraudulent websites. Compared to existing poisoning attacks on RAG systems, our attack is more practical as it does not require access to the target user query's info or edit the user query. It not only ensures that injected texts can be retrieved by the model, but also ensures that the LLM will be misled to refer to the injected texts in its response. We demonstrate the effectiveness of POISONCRAFTacross different datasets, retrievers, and language models in RAG pipelines, and show that it remains effective when transferred across retrievers, including black-box systems. Moreover, we present a case study revealing how the attack influences both the retrieval behavior and the step-by-step reasoning trace within the generation model, and further evaluate the robustness of POISONCRAFTunder multiple defense mechanisms. These results validate the practicality of our threat model and highlight a critical security risk for RAG systems deployed in real-world applications. We release our code\footnote{https://github.com/AndyShaw01/PoisonCraft} to support future research on the security and robustness of RAG systems in real-world settings.
Open AccessPOISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models
Large language models (LLMs) have achieved remarkable success in various domains, primarily due to their strong capabilities in reasoning and generating human-like text. Despite their impressive performance, LLMs are susceptible to hallucinations, which can lead to incorrect or misleading outputs. This is primarily due to the lack of up-to-date knowledge or domain-specific information. Retrieval-augmented generation (RAG) is a promising approach to mitigate hallucinations by leveraging external knowledge sources. However, the security of RAG systems has not been thoroughly studied. In this paper, we study a poisoning attack on RAG systems named POISONCRAFT, which can mislead the model to refer to fraudulent websites. Compared to existing poisoning attacks on RAG systems, our attack is more practical as it does not require access to the target user query's info or edit the user query. It not only ensures that injected texts can be retrieved by the model, but also ensures that the LLM will be misled to refer to the injected texts in its response. We demonstrate the effectiveness of POISONCRAFTacross different datasets, retrievers, and language models in RAG pipelines, and show that it remains effective when transferred across retrievers, including black-box systems. Moreover, we present a case study revealing how the attack influences both the retrieval behavior and the step-by-step reasoning trace within the generation model, and further evaluate the robustness of POISONCRAFTunder multiple defense mechanisms. These results validate the practicality of our threat model and highlight a critical security risk for RAG systems deployed in real-world applications. We release our code\footnote{https://github.com/AndyShaw01/PoisonCraft} to support future research on the security and robustness of RAG systems in real-world settings.
- Open Access
- 14 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 55-56
BandFuzz: A Practical Framework for Collaborative Fuzzing with Reinforcement Learning
In recent years, the technique of collaborative fuzzing has gained prominence as an efficient method for identifying software vulnerabilities. This paper introduces BandFuzz, a distinctive collaborative fuzzing framework designed to intelligently coordinate the use of multiple fuzzers. Unlike previous tools, our approach employs reinforcement learning to enhance both the efficiency and effectiveness of fuzz testing.
- 14 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 55-56
Open AccessBandFuzz: A Practical Framework for Collaborative Fuzzing with Reinforcement Learning
In recent years, the technique of collaborative fuzzing has gained prominence as an efficient method for identifying software vulnerabilities. This paper introduces BandFuzz, a distinctive collaborative fuzzing framework designed to intelligently coordinate the use of multiple fuzzers. Unlike previous tools, our approach employs reinforcement learning to enhance both the efficiency and effectiveness of fuzz testing.