Yuan Jiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuan Jiang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Christoph Treude
Singapore Management University, Singapore
4 shared publications - Tiantian Wang
Harbin Institute of Technology
4 shared publications Xiaohong Su
3 shared publications- Xiaohong Su
Harbin Institute of Technology
2 shared publications Chao Shang
1 shared publicationPengcheng Lu
1 shared publication
Latest Publications
- 2 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 52 (1) , 246-265
Shield Broken: Black-Box Adversarial Attacks on LLM-Based Vulnerability Detectors
Vulnerability detection is critical for ensuring software security. Although deep learning (DL) methods, particularly those employing large language models (LLMs), have shown strong performance in automating vulnerability identification, they remain susceptible to adversarial examples, which are carefully crafted inputs with subtle perturbations designed to evade detection. Existing adversarial attack methods often require access to model architectures or confidence scores, making them impractical for real-world black-box systems. In this paper, we propose SVulAttack, a novel label-only adversarial attack framework targeting LLM-based vulnerability detectors. Our key innovation lies in a similarity-based strategy that estimates statement importance and model confidence, thereby enabling more effective selection of semantic-preserving code perturbations. SVulAttack combines this strategy with a transformation component and a search component, based on either greedy or genetic algorithms, to effectively identify and apply optimal combinations of transformations. We evaluate SVulAttack on open-source models (LineVul, StagedVulBERT, Code Llama, Deepseek-Coder) and closed-source models (GPT-5 nano, GPT-4o, GPT-4o-mini, Claude Sonnet 4). Results show that SVulAttack significantly outperforms existing label-only black-box attack methods. For example, against LineVul, our method with genetic algorithm achieves an attack success rate of 49.0%, improving over DIP and CODA by 150.0% and 240.3%, respectively.
- 2 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 52 (1) , 246-265
Shield Broken: Black-Box Adversarial Attacks on LLM-Based Vulnerability Detectors
Vulnerability detection is critical for ensuring software security. Although deep learning (DL) methods, particularly those employing large language models (LLMs), have shown strong performance in automating vulnerability identification, they remain susceptible to adversarial examples, which are carefully crafted inputs with subtle perturbations designed to evade detection. Existing adversarial attack methods often require access to model architectures or confidence scores, making them impractical for real-world black-box systems. In this paper, we propose SVulAttack, a novel label-only adversarial attack framework targeting LLM-based vulnerability detectors. Our key innovation lies in a similarity-based strategy that estimates statement importance and model confidence, thereby enabling more effective selection of semantic-preserving code perturbations. SVulAttack combines this strategy with a transformation component and a search component, based on either greedy or genetic algorithms, to effectively identify and apply optimal combinations of transformations. We evaluate SVulAttack on open-source models (LineVul, StagedVulBERT, Code Llama, Deepseek-Coder) and closed-source models (GPT-5 nano, GPT-4o, GPT-4o-mini, Claude Sonnet 4). Results show that SVulAttack significantly outperforms existing label-only black-box attack methods. For example, against LineVul, our method with genetic algorithm achieves an attack success rate of 49.0%, improving over DIP and CODA by 150.0% and 240.3%, respectively.
- 7 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 50 (12) , 3454-3471
StagedVulBERT: Multigranular Vulnerability Detection With a Novel Pretrained Code Model
The emergence of pre-trained model-based vulnerability detection methods has significantly advanced the field of automated vulnerability detection. However, these methods still face several challenges, such as difficulty in learning effective feature representations of statements for fine-grained predictions and struggling to process overly long code sequences. To address these issues, this study introduces StagedVulBERT, a novel vulnerability detection framework that leverages a pre-trained code language model and employs a coarse-to-fine strategy. The key innovation and contribution of our research lies in the development of the CodeBERT-HLS component within our framework, specialized in hierarchical, layered, and semantic encoding. This component is designed to capture semantics at both the token and statement levels simultaneously, which is crucial for achieving more accurate multi-granular vulnerability detection. Additionally, CodeBERT-HLS efficiently processes longer code token sequences, making it more suited to real-world vulnerability detection. Comprehensive experiments demonstrate that our method enhances the performance of vulnerability detection at both coarse- and fine-grained levels. Specifically, in coarse-grained vulnerability detection, StagedVulBERT achieves an F1 score of 92.26%, marking a 6.58% improvement over the best-performing methods. At the fine-grained level, our method achieves a Top-5% accuracy of 65.69%, which outperforms the state-of-the-art methods by up to 75.17%.
- 7 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 50 (12) , 3454-3471
StagedVulBERT: Multigranular Vulnerability Detection With a Novel Pretrained Code Model
The emergence of pre-trained model-based vulnerability detection methods has significantly advanced the field of automated vulnerability detection. However, these methods still face several challenges, such as difficulty in learning effective feature representations of statements for fine-grained predictions and struggling to process overly long code sequences. To address these issues, this study introduces StagedVulBERT, a novel vulnerability detection framework that leverages a pre-trained code language model and employs a coarse-to-fine strategy. The key innovation and contribution of our research lies in the development of the CodeBERT-HLS component within our framework, specialized in hierarchical, layered, and semantic encoding. This component is designed to capture semantics at both the token and statement levels simultaneously, which is crucial for achieving more accurate multi-granular vulnerability detection. Additionally, CodeBERT-HLS efficiently processes longer code token sequences, making it more suited to real-world vulnerability detection. Comprehensive experiments demonstrate that our method enhances the performance of vulnerability detection at both coarse- and fine-grained levels. Specifically, in coarse-grained vulnerability detection, StagedVulBERT achieves an F1 score of 92.26%, marking a 6.58% improvement over the best-performing methods. At the fine-grained level, our method achieves a Top-5% accuracy of 65.69%, which outperforms the state-of-the-art methods by up to 75.17%.
- 6 January 2023
- Published by Elsevier in Journal of Systems and Software
- Vol. 198
Does Deep Learning improve the performance of duplicate bug report detection? An empirical study
- 6 January 2023
- Published by Elsevier in Journal of Systems and Software
- Vol. 198
Does Deep Learning improve the performance of duplicate bug report detection? An empirical study
- 6 May 2022
- Published by Elsevier in Journal of Systems and Software
- Vol. 191
Hierarchical semantic-aware neural code representation
- 6 May 2022
- Published by Elsevier in Journal of Systems and Software
- Vol. 191
Hierarchical semantic-aware neural code representation
- 1 August 2020
- Published by Elsevier in Information and Software Technology
- Vol. 124
LTRWES: A new framework for security bug report detection
- 1 August 2020
- Published by Elsevier in Information and Software Technology
- Vol. 124
LTRWES: A new framework for security bug report detection