Yuqing Niu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuqing Niu has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- David Lo
School of Computing and Information Systems, Singapore Management University, Singapore, Singapore
8 shared publications - Chengyan Ma
Singapore Management University
7 shared publications - Ruidong Han
Singapore Management University
7 shared publications - Ye Liu
Singapore Management University
6 shared publications - Debin Gao
Singapore Management University, Singapore, Singapore
3 shared publications - Jieke Shi
Singapore Management University, Singapore, Singapore
3 shared publications
Latest Publications
- 9 October 2026
- Published by Springer Nature
- p. 23-43
Two-Party BBS+ Signature in Two Passes
- Open Access
- 1 October 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (ISSTA) , 4379-4402
On the Evaluation of Large Language Models in Unit Test Evolution (Experience Paper)
Large language models (LLMs) have recently shown promising potential in automating unit test evolution for evolving software systems. However, the effectiveness of LLMs in unit test evolution remains insufficiently understood, particularly with respect to prompt design choices, in-context learning (ICL) strategies, and different types of test evolution. In this paper, we present the first comprehensive empirical study to evaluate LLMs for unit test evolution. We systematically assess nine open-source code LLMs (3B to 34B parameters) and three state-of-the-art commercial models across diverse prompt designs, ICL strategies, and representative test evolution frameworks. To support robust and execution-based evaluation, we construct a new benchmark consisting of 530 real-world focal method–test co-evolution instances collected from seven actively maintained open-source projects. Our evaluation employs a suite of compilation, execution, and coverage-based metrics. Extensive experimental results reveal that prompt design and ICL methods significantly impact LLM effectiveness. Furthermore, the optimal configurations of these strategies vary substantially across different LLMs and evolution types. Based on our findings, we derive actionable insights to guide future research and practical adoption of LLM-based techniques for unit test evolution.
- 1 October 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (ISSTA) , 4379-4402
Open AccessOn the Evaluation of Large Language Models in Unit Test Evolution (Experience Paper)
Large language models (LLMs) have recently shown promising potential in automating unit test evolution for evolving software systems. However, the effectiveness of LLMs in unit test evolution remains insufficiently understood, particularly with respect to prompt design choices, in-context learning (ICL) strategies, and different types of test evolution. In this paper, we present the first comprehensive empirical study to evaluate LLMs for unit test evolution. We systematically assess nine open-source code LLMs (3B to 34B parameters) and three state-of-the-art commercial models across diverse prompt designs, ICL strategies, and representative test evolution frameworks. To support robust and execution-based evaluation, we construct a new benchmark consisting of 530 real-world focal method–test co-evolution instances collected from seven actively maintained open-source projects. Our evaluation employs a suite of compilation, execution, and coverage-based metrics. Extensive experimental results reveal that prompt design and ICL methods significantly impact LLM effectiveness. Furthermore, the optimal configurations of these strategies vary substantially across different LLMs and evolution types. Based on our findings, we derive actionable insights to guide future research and practical adoption of LLM-based techniques for unit test evolution.
- 18 July 2026
- Published by Springer Nature
- p. 401-421
Shielding MCP Tool: A Secure Execution Framework Using TEE and Automated Trimming
- 18 July 2026
- Published by Springer Nature
- p. 401-421
Shielding MCP Tool: A Secure Execution Framework Using TEE and Automated Trimming
- Open Access
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 4551-4574
Automated Repair of TEE Partitioning Issues via DSL-Guided and LLM-Assisted Patching
Trusted Execution Environments (TEEs) provide hardware-based isolation to protect sensitive data and computations from potentially compromised operating systems (OS). However, TEE applications inevitably interact with the untrusted OS through SDK interfaces, and improper partitioning can introduce severe vulnerabilities such as data leakage and code injection. While prior work has proposed static analysis tools to detect such issues, automated repair remains largely unexplored. This problem is particularly challenging due to three TEE-specific factors: the lack of standardized secure development guidelines, the difficulty of extracting semantic information from low-level C code, and the absence of mature testing and validation methods. In this work, we present TEERepair, a framework for automatically repairing bad partitioning issues in TEE applications. Our approach tackles the above challenges by introducing a domain-specific language (DSL) to encode repair rules that express and capture common TEE security patterns, which are instantiated as patch templates with placeholders for context-specific variables. We then leverage large language models (LLMs) to reason about code semantics and synthesize context-aware patches, and further generate test clients to validate the repairs. We evaluate TEERepair on the TEE Partitioning Errors Benchmark (PartitioningE-Bench), achieving a significantly higher repair success rate of 87.6% compared to baselines. Furthermore, applying TEERepair to real-world TEE projects, we submitted 5 repair pull requests, 2 of which have been confirmed and merged by project maintainers.
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 4551-4574
Open AccessAutomated Repair of TEE Partitioning Issues via DSL-Guided and LLM-Assisted Patching
Trusted Execution Environments (TEEs) provide hardware-based isolation to protect sensitive data and computations from potentially compromised operating systems (OS). However, TEE applications inevitably interact with the untrusted OS through SDK interfaces, and improper partitioning can introduce severe vulnerabilities such as data leakage and code injection. While prior work has proposed static analysis tools to detect such issues, automated repair remains largely unexplored. This problem is particularly challenging due to three TEE-specific factors: the lack of standardized secure development guidelines, the difficulty of extracting semantic information from low-level C code, and the absence of mature testing and validation methods. In this work, we present TEERepair, a framework for automatically repairing bad partitioning issues in TEE applications. Our approach tackles the above challenges by introducing a domain-specific language (DSL) to encode repair rules that express and capture common TEE security patterns, which are instantiated as patch templates with placeholders for context-specific variables. We then leverage large language models (LLMs) to reason about code semantics and synthesize context-aware patches, and further generate test clients to validate the repairs. We evaluate TEERepair on the TEE Partitioning Errors Benchmark (PartitioningE-Bench), achieving a significantly higher repair success rate of 87.6% compared to baselines. Furthermore, applying TEERepair to real-world TEE projects, we submitted 5 repair pull requests, 2 of which have been confirmed and merged by project maintainers.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 155-159
PatchGPT: Multi-Agent Patch Backporting without Model Fine-Tuning
Patch backporting is crucial and prevalent in the maintenance of modern open-source software such as Linux kernels and forked repositories. However, porting patches across program versions remains a challenging problem due to the complexity of synergizing diverse patches with divergent program versions. In this paper, we propose PatchGPT, an agentic patch backporting framework for fine-grained patch generation. PatchGPT encompasses three agents: Miner for decomposing a sequence of atomic change steps as the original patch plan, Adapter for adapting the patch plan, and Executor for executing the adapted patch plan according to predefined change semantics. We conduct experiments on the PPatHF’s benchmark containing 310 Vim-NeoVim patch pairs. The experiment results indicate that PatchGPT not only achieves a success rate of up to 50.96%, outperforming PPatHF by 8.71%, but also provides actionable insights into the reasoning process behind patch generation and adaptation.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 155-159
Open AccessPatchGPT: Multi-Agent Patch Backporting without Model Fine-Tuning
Patch backporting is crucial and prevalent in the maintenance of modern open-source software such as Linux kernels and forked repositories. However, porting patches across program versions remains a challenging problem due to the complexity of synergizing diverse patches with divergent program versions. In this paper, we propose PatchGPT, an agentic patch backporting framework for fine-grained patch generation. PatchGPT encompasses three agents: Miner for decomposing a sequence of atomic change steps as the original patch plan, Adapter for adapting the patch plan, and Executor for executing the adapted patch plan according to predefined change semantics. We conduct experiments on the PPatHF’s benchmark containing 310 Vim-NeoVim patch pairs. The experiment results indicate that PatchGPT not only achieves a success rate of up to 50.96%, outperforming PPatHF by 8.71%, but also provides actionable insights into the reasoning process behind patch generation and adaptation.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 110-115
Finding Missing Input Validation in TEEs via LLM-Assisted Symbolic Execution
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 110-115
Open AccessFinding Missing Input Validation in TEEs via LLM-Assisted Symbolic Execution
- 2 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 52 (4) , 1549-1567
Towards Secure Program Partitioning for Smart Contracts With LLM’s In-Context Learning
Smart contracts are highly susceptible to manipulation attacks due to the leakage of sensitive information. Addressing manipulation vulnerabilities is particularly challenging because they stem from inherent data confidentiality issues rather than straightforward implementation bugs. To tackle this by preventing sensitive information leakage, we present PARTITIONGPT, the first LLM-driven approach that combines static analysis with the in-context learning capabilities of large language models (LLMs) to partition smart contracts into critical (privileged) and normal codebases, guided by a few annotated sensitive data variables. We evaluated PARTITIONGPT on 18 annotated smart contracts containing 99 sensitive functions. The results demonstrate that PARTITIONGPT successfully generates compilable, and verified partitions, achieving a precision of 80% while reducing more than 26% code compared to functionlevel partitioning approach. Furthermore, we evaluated PARTITIONGPT on nine real-world manipulation attacks that led to a total loss of 25 million dollars, PARTITIONGPT effectively prevents eight cases, highlighting its potential for broad applicability and the necessity for secure program partitioning during smart contract development to diminish manipulation vulnerabilities.
- 2 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 52 (4) , 1549-1567
Towards Secure Program Partitioning for Smart Contracts With LLM’s In-Context Learning
Smart contracts are highly susceptible to manipulation attacks due to the leakage of sensitive information. Addressing manipulation vulnerabilities is particularly challenging because they stem from inherent data confidentiality issues rather than straightforward implementation bugs. To tackle this by preventing sensitive information leakage, we present PARTITIONGPT, the first LLM-driven approach that combines static analysis with the in-context learning capabilities of large language models (LLMs) to partition smart contracts into critical (privileged) and normal codebases, guided by a few annotated sensitive data variables. We evaluated PARTITIONGPT on 18 annotated smart contracts containing 99 sensitive functions. The results demonstrate that PARTITIONGPT successfully generates compilable, and verified partitions, achieving a precision of 80% while reducing more than 26% code compared to functionlevel partitioning approach. Furthermore, we evaluated PARTITIONGPT on nine real-world manipulation attacks that led to a total loss of 25 million dollars, PARTITIONGPT effectively prevents eight cases, highlighting its potential for broad applicability and the necessity for secure program partitioning during smart contract development to diminish manipulation vulnerabilities.
- 21 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 52 (3) , 923-938
Automated TEE Adaptation With LLMs: Identifying, Transforming, and Porting Sensitive Functions in Programs
Trusted Execution Environments (TEEs) isolate a special space within a device’s memory that is not accessible to the normal world (also known as the untrusted environment), even when the device is compromised. Therefore, developers can utilize TEEs to provide robust security guarantees for their programs, protecting sensitive operations, such as encrypted data storage, fingerprint verification, and remote attestation, from software-based attacks. Despite the robust protections offered by TEEs, adapting existing programs to leverage such security guarantees is challenging, often requiring extensive domain knowledge and manual intervention, which makes TEEs less accessible to developers. This motivates us to design AUTOTEE, the first Large Language Model (LLM) enabled approach that can automatically identify, transform, and port functions containing sensitive operations into TEEs with minimal developer intervention. By manually reviewing 68 repositories, we constructed a benchmark dataset consisting of 385 sensitive functions eligible for transformation, on which AUTOTEE achieves a F1 score of 0.94 on Java and 0.87 on Python. AUTOTEE effectively transforms these sensitive functions into TEE-compatible versions, achieving success rates of 91.8% and 84.3% for Java and Python, respectively, when using GPT-4o.
- 21 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 52 (3) , 923-938
Automated TEE Adaptation With LLMs: Identifying, Transforming, and Porting Sensitive Functions in Programs
Trusted Execution Environments (TEEs) isolate a special space within a device’s memory that is not accessible to the normal world (also known as the untrusted environment), even when the device is compromised. Therefore, developers can utilize TEEs to provide robust security guarantees for their programs, protecting sensitive operations, such as encrypted data storage, fingerprint verification, and remote attestation, from software-based attacks. Despite the robust protections offered by TEEs, adapting existing programs to leverage such security guarantees is challenging, often requiring extensive domain knowledge and manual intervention, which makes TEEs less accessible to developers. This motivates us to design AUTOTEE, the first Large Language Model (LLM) enabled approach that can automatically identify, transform, and port functions containing sensitive operations into TEEs with minimal developer intervention. By manually reviewing 68 repositories, we constructed a benchmark dataset consisting of 385 sensitive functions eligible for transformation, on which AUTOTEE achieves a F1 score of 0.94 on Java and 0.87 on Python. AUTOTEE effectively transforms these sensitive functions into TEE-compatible versions, achieving success rates of 91.8% and 84.3% for Java and Python, respectively, when using GPT-4o.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11687-11696
Do Existing Testing Tools Really Uncover Gender Bias in Text-to-Image Models?
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11687-11696
Open AccessDo Existing Testing Tools Really Uncover Gender Bias in Text-to-Image Models?