Yuan Xiao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuan Xiao has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Chunrong Fang
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China
8 shared publications - Yuchen Chen
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China
7 shared publications - Zhenyu Chen
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China
7 shared publications - Weisong Sun
Nanyang technological university, Singapore, Singapore
6 shared publications - Baowen Xu
Nanjing University, Nanjing, China
5 shared publications - Yang Liu
Department of Obstetrics and Gynecology, The Second Affiliated Hospital of Kunming Medical University, China
4 shared publications
Latest Publications
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1182-1194
Breaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor Attacks
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1182-1194
Open AccessBreaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor Attacks
- Open Access
- 1 October 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (ISSTA) , 1809-1831
Insecure Coding Preferences in Long-Term Memory: Security Risks for LLM-Based Code Generation
LLM-based systems increasingly incorporate long-term memory to improve cross-session continuity. However, once insecure coding preferences are stored, they may silently influence security-critical decisions in subsequent generations. In this study, we conduct the first systematic empirical study on the impact of insecure coding preferences stored in long-term memory on the security of LLM-based code generation. We evaluate four LLMs (ChatGPT, Gemini, Qwen, and Grok) across five programming languages (Python, C, C++, Go, and JavaScript). Our results show that insecure memories significantly increase the risk of generating vulnerable code by 2.7-50.3 percentage points (pp). Moreover, they create a 5.4-14.0 percentage-point risk-warning gap, where warning-rate increases lag behind vulnerability-rate increases. Further analysis reveals that insecure memories are difficult to overwrite through normal interactions and can broadly influence model outputs even when prompts are phrased differently. Finally, we evaluate three mitigation strategies: security-requirement appending and memory storage reduce vulnerability rates by 19.7-33.6 pp but may degrade functional correctness by up to 15.9 pp; memory-level safety filtering achieves a 100% detection rate on our evaluated risky memory entries and restores generation behavior to the without-memory baseline. Based on these findings, we provide actionable suggestions to improve the security of long-term memory in LLM-based code generation.
- 1 October 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (ISSTA) , 1809-1831
Open AccessInsecure Coding Preferences in Long-Term Memory: Security Risks for LLM-Based Code Generation
LLM-based systems increasingly incorporate long-term memory to improve cross-session continuity. However, once insecure coding preferences are stored, they may silently influence security-critical decisions in subsequent generations. In this study, we conduct the first systematic empirical study on the impact of insecure coding preferences stored in long-term memory on the security of LLM-based code generation. We evaluate four LLMs (ChatGPT, Gemini, Qwen, and Grok) across five programming languages (Python, C, C++, Go, and JavaScript). Our results show that insecure memories significantly increase the risk of generating vulnerable code by 2.7-50.3 percentage points (pp). Moreover, they create a 5.4-14.0 percentage-point risk-warning gap, where warning-rate increases lag behind vulnerability-rate increases. Further analysis reveals that insecure memories are difficult to overwrite through normal interactions and can broadly influence model outputs even when prompts are phrased differently. Finally, we evaluate three mitigation strategies: security-requirement appending and memory storage reduce vulnerability rates by 19.7-33.6 pp but may degrade functional correctness by up to 15.9 pp; memory-level safety filtering achieves a 100% detection rate on our evaluated risky memory entries and restores generation behavior to the without-memory baseline. Based on these findings, we provide actionable suggestions to improve the security of long-term memory in LLM-based code generation.
- Open Access
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 590-612
PuzzleMark: Implicit Jigsaw Learning for Robust Code Dataset Watermarking in Neural Code Completion Models
Constructing and curating high-quality code datasets requires significant resources, making them valuable intellectual property. Unfortunately, these datasets currently face severe risks of unauthorized use. Although digital watermarking offers a post hoc mechanism for copyright authentication, existing methods are predominantly based on the co-occurrence pattern, which is not robust and is susceptible to watermark detection and removal attacks. In this paper, we propose PuzzleMark, a robust watermarking method for code datasets. To reduce the risk of watermark exposure, PuzzleMark introduces a carrier selection strategy that leverages code complexity to evaluate the suitability of code snippets as watermark carriers, and selects those with high suitability for watermarking. To enhance the robustness of the watermark, PuzzleMark proposes a novel concatenation pattern to replace the traditional co-occurrence pattern, and implements two watermarking strategies through variable name concatenation. PuzzleMark adaptively embeds watermarks based on the inherent characteristics of the code, making it more stealthy while maintaining design simplicity. For watermark verification, PuzzleMark employs Fisher’s exact test to verify suspicious models under a black-box setting. Experimental results demonstrate that PuzzleMark achieves a 100 percent verification success rate and a 0 percent false positive rate, with negligible impact on model performance. Both our human study and our evaluation using four state-of-the-art watermark detection methods show that PuzzleMark exhibits strong imperceptibility, with an average suspicious rate ≤ 0.24 and an average recall ≤ 30.41 percent, respectively. Furthermore, the consistent retention of verifiability under two attack scenarios further corroborates the robustness of PuzzleMark. As a practical digital watermarking method, PuzzleMark provides strong protection for the intellectual property of code datasets and offers new insights for future research.
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 590-612
Open AccessPuzzleMark: Implicit Jigsaw Learning for Robust Code Dataset Watermarking in Neural Code Completion Models
Constructing and curating high-quality code datasets requires significant resources, making them valuable intellectual property. Unfortunately, these datasets currently face severe risks of unauthorized use. Although digital watermarking offers a post hoc mechanism for copyright authentication, existing methods are predominantly based on the co-occurrence pattern, which is not robust and is susceptible to watermark detection and removal attacks. In this paper, we propose PuzzleMark, a robust watermarking method for code datasets. To reduce the risk of watermark exposure, PuzzleMark introduces a carrier selection strategy that leverages code complexity to evaluate the suitability of code snippets as watermark carriers, and selects those with high suitability for watermarking. To enhance the robustness of the watermark, PuzzleMark proposes a novel concatenation pattern to replace the traditional co-occurrence pattern, and implements two watermarking strategies through variable name concatenation. PuzzleMark adaptively embeds watermarks based on the inherent characteristics of the code, making it more stealthy while maintaining design simplicity. For watermark verification, PuzzleMark employs Fisher’s exact test to verify suspicious models under a black-box setting. Experimental results demonstrate that PuzzleMark achieves a 100 percent verification success rate and a 0 percent false positive rate, with negligible impact on model performance. Both our human study and our evaluation using four state-of-the-art watermark detection methods show that PuzzleMark exhibits strong imperceptibility, with an average suspicious rate ≤ 0.24 and an average recall ≤ 30.41 percent, respectively. Furthermore, the consistent retention of verifiability under two attack scenarios further corroborates the robustness of PuzzleMark. As a practical digital watermarking method, PuzzleMark provides strong protection for the intellectual property of code datasets and offers new insights for future research.
- Open Access
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 1059-1081
DuCodeMark: Dual-Purpose Code Dataset Watermarking via Style-Aware Watermark-Poison Design
The proliferation of large language models for code (CodeLMs) and open-source contributions has heightened concerns over unauthorized use of source code datasets. While watermarking provides a viable protection mechanism by embedding ownership signals, existing methods rely on detectable trigger-target patterns and are limited to source-code tasks, overlooking other scenarios such as decompilation tasks. In this paper, we propose DuCodeMark, a stealthy and robust dual-purpose watermarking method for code datasets that generalizes across both source-code tasks and decompilation tasks. DuCodeMark parses each code sample into an abstract syntax tree (AST), applies language-specific style transformations to construct stealthy trigger-target pairs, and injects repressible poisoned features into a subset of return-typed samples to enhance robustness against watermark removal or evasion. These features remain inactive during normal training but are activated upon watermark removal, degrading model performance. For verification, DuCodeMark employs a black-box method based on the independent-samples t -test. We conduct a comprehensive evaluation of DuCodeMark across 72 settings spanning two code tasks, two programming languages, three CodeLMs, and six decoding temperatures. The results demonstrate that it consistently achieves strong verifiability ( p < 0.05), high stealthiness (suspicion rate ≤ 0.36), robustness against both watermark and poisoning attacks (recall ≤ 0.57), and a substantial drop in model performance upon watermark removal (Pass@1 drops by 28.6
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 1059-1081
Open AccessDuCodeMark: Dual-Purpose Code Dataset Watermarking via Style-Aware Watermark-Poison Design
The proliferation of large language models for code (CodeLMs) and open-source contributions has heightened concerns over unauthorized use of source code datasets. While watermarking provides a viable protection mechanism by embedding ownership signals, existing methods rely on detectable trigger-target patterns and are limited to source-code tasks, overlooking other scenarios such as decompilation tasks. In this paper, we propose DuCodeMark, a stealthy and robust dual-purpose watermarking method for code datasets that generalizes across both source-code tasks and decompilation tasks. DuCodeMark parses each code sample into an abstract syntax tree (AST), applies language-specific style transformations to construct stealthy trigger-target pairs, and injects repressible poisoned features into a subset of return-typed samples to enhance robustness against watermark removal or evasion. These features remain inactive during normal training but are activated upon watermark removal, degrading model performance. For verification, DuCodeMark employs a black-box method based on the independent-samples t -test. We conduct a comprehensive evaluation of DuCodeMark across 72 settings spanning two code tasks, two programming languages, three CodeLMs, and six decoding temperatures. The results demonstrate that it consistently achieves strong verifiability ( p < 0.05), high stealthiness (suspicion rate ≤ 0.36), robustness against both watermark and poisoning attacks (recall ≤ 0.57), and a substantial drop in model performance upon watermark removal (Pass@1 drops by 28.6
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 52 (10) , 1-18
Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language Models
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 52 (10) , 1-18
Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language Models
- Open Access
- 22 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 2 (ISSTA) , 1701-1724
DeCoMa: Detecting and Purifying Code Dataset Watermarks through Dual Channel Code Abstraction
Watermarking is a technique to help identify the source of data points, which can be used to help prevent the misuse of protected datasets. Existing methods on code watermarking, leveraging the idea from the backdoor research, embed stealthy triggers as watermarks. Despite their high resilience against dilution attacks and backdoor detections, the robustness has not been fully evaluated. To fill this gap, we propose DeCoMa , a dual-channel approach to De tect and purify Co de dataset water Ma rks. To overcome the high barrier created by the stealthy and hidden nature of code watermarks, DeCoMa leverages dual-channel constraints on code to generalize and map code samples into standardized templates. Subsequently, DeCoMa extracts hidden watermarks by identifying outlier associations between paired elements within the standardized templates. Finally, DeCoMa purifies the watermarked dataset by removing all samples containing the detected watermark, enabling the silent appropriation of protected code. We conduct extensive experiments to evaluate the effectiveness and efficiency of DeCoMa, covering 14 types of code watermarks and 3 representative intelligent code tasks (a total of 14 scenarios). Experimental results demonstrate that DeCoMa achieves a stable recall of 100% in 14 code watermark detection scenarios, significantly outperforming the baselines. Additionally, DeCoMa effectively attacks code watermarks with embedding rates as low as 0.1%, while maintaining comparable model performance after training on the purified dataset. Furthermore, as DeCoMa requires no model training for detection, it achieves substantially higher efficiency than all baselines, with a speedup ranging from 31.5 to 130.9×. The results call for more advanced watermarking techniques for code models, while DeCoMa can serve as a baseline for future evaluation.
- 22 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 2 (ISSTA) , 1701-1724
Open AccessDeCoMa: Detecting and Purifying Code Dataset Watermarks through Dual Channel Code Abstraction
Watermarking is a technique to help identify the source of data points, which can be used to help prevent the misuse of protected datasets. Existing methods on code watermarking, leveraging the idea from the backdoor research, embed stealthy triggers as watermarks. Despite their high resilience against dilution attacks and backdoor detections, the robustness has not been fully evaluated. To fill this gap, we propose DeCoMa , a dual-channel approach to De tect and purify Co de dataset water Ma rks. To overcome the high barrier created by the stealthy and hidden nature of code watermarks, DeCoMa leverages dual-channel constraints on code to generalize and map code samples into standardized templates. Subsequently, DeCoMa extracts hidden watermarks by identifying outlier associations between paired elements within the standardized templates. Finally, DeCoMa purifies the watermarked dataset by removing all samples containing the detected watermark, enabling the silent appropriation of protected code. We conduct extensive experiments to evaluate the effectiveness and efficiency of DeCoMa, covering 14 types of code watermarks and 3 representative intelligent code tasks (a total of 14 scenarios). Experimental results demonstrate that DeCoMa achieves a stable recall of 100% in 14 code watermark detection scenarios, significantly outperforming the baselines. Additionally, DeCoMa effectively attacks code watermarks with embedding rates as low as 0.1%, while maintaining comparable model performance after training on the purified dataset. Furthermore, as DeCoMa requires no model training for detection, it achieves substantially higher efficiency than all baselines, with a speedup ranging from 31.5 to 130.9×. The results call for more advanced watermarking techniques for code models, while DeCoMa can serve as a baseline for future evaluation.
- Open Access
- 19 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 2 (FSE) , 1386-1408
Eliminating Backdoors in Neural Code Models for Secure Code Understanding
Neural code models (NCMs) have been widely used to address various code understanding tasks, such as defect detection. However, numerous recent studies reveal that such models are vulnerable to backdoor attacks. Backdoored NCMs function normally on normal/clean code snippets, but exhibit adversary-expected behavior on poisoned code snippets injected with the adversary-crafted trigger. It poses a significant security threat. For example, a backdoored defect detection model may misclassify user-submitted defective code as non-defective. If this insecure code is then integrated into critical systems, like autonomous driving systems, it could jeopardize life safety. Therefore, there is an urgent need for effective techniques to detect and eliminate backdoors stealthily implanted in NCMs. To address this issue, in this paper, we innovatively propose a backdoor elimination technique for secure code understanding, called EliBadCode. EliBadCode eliminates backdoors in NCMs by inverting/reverse-engineering and unlearning backdoor triggers. Specifically, EliBadCode first filters the model vocabulary for trigger tokens based on the naming conventions of specific programming languages to reduce the trigger search space and cost. Then, EliBadCode introduces a sample-specific trigger position identification method, which can reduce the interference of non-backdoor ( adversarial ) perturbations for subsequent trigger inversion, thereby producing effective inverted backdoor triggers efficiently. Backdoor triggers can be viewed as backdoor ( adversarial ) perturbations . Subsequently, EliBadCode employs a Greedy Coordinate Gradient algorithm to optimize the inverted trigger and designs a trigger anchoring method to purify the inverted trigger. Finally, EliBadCode eliminates backdoors through model unlearning. We evaluate the effectiveness of in eliminating backdoors implanted in multiple NCMs used for three safety-critical code understanding tasks. The results demonstrate that EliBadCode can effectively eliminate backdoors while having minimal adverse effects on the normal functionality of the model. For instance, on defect detection tasks, EliBadCode substantially decreases the average Attack Success Rate (ASR) of the advanced backdoor attack from 99.76% to 2.64%, significantly outperforming the three baselines. The clean model produced by EliBadCode exhibits an average decrease in defect prediction accuracy of only 0.01% (the same as the baseline).
- 19 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 2 (FSE) , 1386-1408
Open AccessEliminating Backdoors in Neural Code Models for Secure Code Understanding
Neural code models (NCMs) have been widely used to address various code understanding tasks, such as defect detection. However, numerous recent studies reveal that such models are vulnerable to backdoor attacks. Backdoored NCMs function normally on normal/clean code snippets, but exhibit adversary-expected behavior on poisoned code snippets injected with the adversary-crafted trigger. It poses a significant security threat. For example, a backdoored defect detection model may misclassify user-submitted defective code as non-defective. If this insecure code is then integrated into critical systems, like autonomous driving systems, it could jeopardize life safety. Therefore, there is an urgent need for effective techniques to detect and eliminate backdoors stealthily implanted in NCMs. To address this issue, in this paper, we innovatively propose a backdoor elimination technique for secure code understanding, called EliBadCode. EliBadCode eliminates backdoors in NCMs by inverting/reverse-engineering and unlearning backdoor triggers. Specifically, EliBadCode first filters the model vocabulary for trigger tokens based on the naming conventions of specific programming languages to reduce the trigger search space and cost. Then, EliBadCode introduces a sample-specific trigger position identification method, which can reduce the interference of non-backdoor ( adversarial ) perturbations for subsequent trigger inversion, thereby producing effective inverted backdoor triggers efficiently. Backdoor triggers can be viewed as backdoor ( adversarial ) perturbations . Subsequently, EliBadCode employs a Greedy Coordinate Gradient algorithm to optimize the inverted trigger and designs a trigger anchoring method to purify the inverted trigger. Finally, EliBadCode eliminates backdoors through model unlearning. We evaluate the effectiveness of in eliminating backdoors implanted in multiple NCMs used for three safety-critical code understanding tasks. The results demonstrate that EliBadCode can effectively eliminate backdoors while having minimal adverse effects on the normal functionality of the model. For instance, on defect detection tasks, EliBadCode substantially decreases the average Attack Success Rate (ASR) of the advanced backdoor attack from 99.76% to 2.64%, significantly outperforming the three baselines. The clean model produced by EliBadCode exhibits an average decrease in defect prediction accuracy of only 0.01% (the same as the baseline).
- Open Access
- 11 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 1453-1465
CooTest: An Automated Testing Approach for V2X Communication Systems
Perceiving the complex driving environment precisely is crucial to the safe operation of autonomous vehicles. With the tremendous advancement of deep learning and communication technology, Vehicle-to-Everything (V2X) collaboration has the potential to address limitations in sensing distant objects and occlusion for a single-agent perception system. However, despite spectacular progress, several communication challenges can undermine the effectiveness of multi-vehicle cooperative perception. The low interpretability of Deep Neural Networks (DNNs) and the high complexity of communication mechanisms make conventional testing techniques inapplicable for the cooperative perception of autonomous driving systems (ADS). Besides, the existing testing techniques, depending on manual data collection and labeling, become time-consuming and prohibitively expensive. In this paper, we design and implement CooTest, the first automated testing tool of the V2X-oriented cooperative perception module. CooTest devises the V2X-specific metamorphic relation and equips communication and weather transformation operators that can reflect the impact of the various cooperative driving factors to produce transformed scenes. Furthermore, we adopt a V2X-oriented guidance strategy for the transformed scene generation process and improve testing efficiency. We experiment CooTest with multiple cooperative perception models with different fusion schemes to evaluate its performance on different tasks. The experiment results show that CooTest can effectively detect erroneous behaviors under various V2X-oriented driving conditions. Also, the results confirm that CooTest can improve detection average precision and decrease misleading cooperation errors by retraining with the generated scenes.
- 11 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 1453-1465
Open AccessCooTest: An Automated Testing Approach for V2X Communication Systems
Perceiving the complex driving environment precisely is crucial to the safe operation of autonomous vehicles. With the tremendous advancement of deep learning and communication technology, Vehicle-to-Everything (V2X) collaboration has the potential to address limitations in sensing distant objects and occlusion for a single-agent perception system. However, despite spectacular progress, several communication challenges can undermine the effectiveness of multi-vehicle cooperative perception. The low interpretability of Deep Neural Networks (DNNs) and the high complexity of communication mechanisms make conventional testing techniques inapplicable for the cooperative perception of autonomous driving systems (ADS). Besides, the existing testing techniques, depending on manual data collection and labeling, become time-consuming and prohibitively expensive. In this paper, we design and implement CooTest, the first automated testing tool of the V2X-oriented cooperative perception module. CooTest devises the V2X-specific metamorphic relation and equips communication and weather transformation operators that can reflect the impact of the various cooperative driving factors to produce transformed scenes. Furthermore, we adopt a V2X-oriented guidance strategy for the transformed scene generation process and improve testing efficiency. We experiment CooTest with multiple cooperative perception models with different fusion schemes to evaluate its performance on different tasks. The experiment results show that CooTest can effectively detect erroneous behaviors under various V2X-oriented driving conditions. Also, the results confirm that CooTest can improve detection average precision and decrease misleading cooperation errors by retraining with the generated scenes.