Yuxin Su
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuxin Su has a total of 88 co-authors. Here are the top co-authors by number of shared publications:
- Michael R. Lyu
The Chinese University of Hong Kong
17 shared publications - Zibin Zheng
Sun Yat-Sen University, Guangzhou, China
7 shared publications - Shiwen Shan
Sun Yat-sen University, Zhuhai, China
5 shared publications - Cheryl Lee
The Chinese University of Hong Kong
4 shared publications - Jiacheng Shen
Duke Kunshan University, Kunshan, China
4 shared publications - Yintong Huo
Singapore Management University, Singapore
4 shared publications
Latest Publications
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
ASIDE: From Conflict Participants to Co-Observers Through Dyadic Spectator Reflection
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessASIDE: From Conflict Participants to Co-Observers Through Dyadic Spectator Reflection
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 4128-4138
Li-WaC: A Lightweight WebAssembly Container for Independently Upgradable IoT Applications in Xiaomi Vela
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 4128-4138
Open AccessLi-WaC: A Lightweight WebAssembly Container for Independently Upgradable IoT Applications in Xiaomi Vela
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1396-1408
MicroAgent: Context-Augmented Multi-agent Framework for Automatic Microservice Decomposition
The adoption of Microservice Architecture (MSA) has revolutionized software engineering by enhancing scalability, agility, and maintainability over traditional monolithic applications. As more developers transition their legacy systems to microservice-based architectures, effective microservice decomposition—partitioning monolithic applications into highly cohesive services—becomes vital. However, this decomposition task presents significant challenges. Manual approaches are time-consuming and labor-intensive. Existing automated methods often fail to capture the necessary semantic insights from complex applications, while naive applications of Large Language Models tend to overlook crucial contextual information and design principles, leading to suboptimal results. To address these challenges, we propose MicroAgent, a Context-Augmented Multi-Agent Framework for Microservice Decomposition. Our framework divides the decomposition process into five distinct subtasks and assigns each to a specialized agent. To enhance the effectiveness of each agent, we provide tailored, multi-granularity context that keeps its analysis focused and mitigates information overload. Furthermore, to ensure the decomposition adheres to established design principles, we integrate analytical tools that guide the agents’ decision-making. Experimental evaluations on 10 Java Web applications demonstrate that MicroAgent achieves an average decomposition accuracy of 89.2%, outperforming the state-of-the-art method by 24.6%. We also conduct a case study to highlight the practical benefits of our design.
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1396-1408
Open AccessMicroAgent: Context-Augmented Multi-agent Framework for Automatic Microservice Decomposition
The adoption of Microservice Architecture (MSA) has revolutionized software engineering by enhancing scalability, agility, and maintainability over traditional monolithic applications. As more developers transition their legacy systems to microservice-based architectures, effective microservice decomposition—partitioning monolithic applications into highly cohesive services—becomes vital. However, this decomposition task presents significant challenges. Manual approaches are time-consuming and labor-intensive. Existing automated methods often fail to capture the necessary semantic insights from complex applications, while naive applications of Large Language Models tend to overlook crucial contextual information and design principles, leading to suboptimal results. To address these challenges, we propose MicroAgent, a Context-Augmented Multi-Agent Framework for Microservice Decomposition. Our framework divides the decomposition process into five distinct subtasks and assigns each to a specialized agent. To enhance the effectiveness of each agent, we provide tailored, multi-granularity context that keeps its analysis focused and mitigates information overload. Furthermore, to ensure the decomposition adheres to established design principles, we integrate analytical tools that guide the agents’ decision-making. Experimental evaluations on 10 Java Web applications demonstrate that MicroAgent achieves an average decomposition accuracy of 89.2%, outperforming the state-of-the-art method by 24.6%. We also conduct a case study to highlight the practical benefits of our design.
- Open Access
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 2465-2487
VulKey: Automated Vulnerability Repair Guided by Domain-Specific Repair Patterns
The increasing prevalence of software vulnerabilities highlights the need for effective Automatic Vulnerability Repair (AVR) tools. While LLM-based approaches are promising, they struggle to incorporate structured security knowledge from sources like CWE and NVD. Current methods either use this information superficially by concatenating the CWE-ID into the input prompt, yielding negligible benefits, or rely on few-shot learning with rigid, non-generalizable examples, which limits their effectiveness in real-world scenarios. To address this gap, we propose VulKey, an LLM-based AVR framework that leverages a hierarchical abstraction of expert knowledge to guide patch generation. Our novel three-level abstraction formulates repair strategies in terms of CWE type, syntactic actions, and semantic key elements. This approach captures the essence of a security fix with greater generality than concrete examples and more semantic richness than traditional syntax-based templates, overcoming the coverage limitations of prior methods. VulKey is implemented as a two-stage pipeline: first, expert knowledge matching predicts an appropriate repair pattern for the vulnerability; second, repair code generation uses a pattern-guided, fine-tuned LLM to produce secure patches. On the real-world C/C++ dataset PrimeVul, VulKey achieves 31.5% repair accuracy, surpassing the best baseline by 7.6% and outperforming leading tools such as VulMaster and GPT-5. Moreover, VulKey demonstrates cross-language and cross-model generalizability, with state-of-the-art performance on the Java benchmark Vul4J. These results underscore the importance of structured expert knowledge in advancing AVR effectiveness. Our work demonstrates that explicitly modeling and integrating expert security knowledge through hierarchical patterns is a crucial step toward building more effective and reliable AVR tools.
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 2465-2487
Open AccessVulKey: Automated Vulnerability Repair Guided by Domain-Specific Repair Patterns
The increasing prevalence of software vulnerabilities highlights the need for effective Automatic Vulnerability Repair (AVR) tools. While LLM-based approaches are promising, they struggle to incorporate structured security knowledge from sources like CWE and NVD. Current methods either use this information superficially by concatenating the CWE-ID into the input prompt, yielding negligible benefits, or rely on few-shot learning with rigid, non-generalizable examples, which limits their effectiveness in real-world scenarios. To address this gap, we propose VulKey, an LLM-based AVR framework that leverages a hierarchical abstraction of expert knowledge to guide patch generation. Our novel three-level abstraction formulates repair strategies in terms of CWE type, syntactic actions, and semantic key elements. This approach captures the essence of a security fix with greater generality than concrete examples and more semantic richness than traditional syntax-based templates, overcoming the coverage limitations of prior methods. VulKey is implemented as a two-stage pipeline: first, expert knowledge matching predicts an appropriate repair pattern for the vulnerability; second, repair code generation uses a pattern-guided, fine-tuned LLM to produce secure patches. On the real-world C/C++ dataset PrimeVul, VulKey achieves 31.5% repair accuracy, surpassing the best baseline by 7.6% and outperforming leading tools such as VulMaster and GPT-5. Moreover, VulKey demonstrates cross-language and cross-model generalizability, with state-of-the-art performance on the Java benchmark Vul4J. These results underscore the importance of structured expert knowledge in advancing AVR effectiveness. Our work demonstrates that explicitly modeling and integrating expert security knowledge through hierarchical patterns is a crucial step toward building more effective and reliable AVR tools.
- 28 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 4801-4815
Revealing Honeypots in High-Frequency Interactions on Decentralized Applications
The development of decentralized finance on blockchains leads to increasing high-frequency traders interacting with decentralized applications (DApps) to earn profits. However, DApps have a deficiency during high-frequency interactions: transaction records generated by these interactions are freely accessible on blockchains. If a user has high-frequency interactions with DApps, his transaction patterns can be exposed to attackers. Attackers can predict the conditions under which a user will execute transactions and the parameters a user will use. Due to the transparency of pending transactions, attackers can build honeypots to trick them into performing certain actions, resulting in significant security risks. This study presents the first formal definition of the honeypot in high-frequency interactions on DApps. We introduce matching rules and propose a log-based transaction parsing method to detect honeypots caused by the deficiency. Our method finds that 99 smart contracts are affected by 636 incidents, resulting in losses exceeding 25M USD. When a honeypot transaction occurs, the victim’s transaction is reverted, underscoring the importance of understanding the underlying causes. However, analyzing revert causes directly from transaction input data poses challenges, especially when the victim’s contract is not opensource. To address this challenge, we introduce a novel frequent mining method to analyze the causes of honeypots. The recovery success rate reaches 82.39%. Based on the causes that lead to transaction reverts, we propose potential strategies to mitigate these security risks and validate them in a simulated environment.
- 28 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 4801-4815
Revealing Honeypots in High-Frequency Interactions on Decentralized Applications
The development of decentralized finance on blockchains leads to increasing high-frequency traders interacting with decentralized applications (DApps) to earn profits. However, DApps have a deficiency during high-frequency interactions: transaction records generated by these interactions are freely accessible on blockchains. If a user has high-frequency interactions with DApps, his transaction patterns can be exposed to attackers. Attackers can predict the conditions under which a user will execute transactions and the parameters a user will use. Due to the transparency of pending transactions, attackers can build honeypots to trick them into performing certain actions, resulting in significant security risks. This study presents the first formal definition of the honeypot in high-frequency interactions on DApps. We introduce matching rules and propose a log-based transaction parsing method to detect honeypots caused by the deficiency. Our method finds that 99 smart contracts are affected by 636 incidents, resulting in losses exceeding 25M USD. When a honeypot transaction occurs, the victim’s transaction is reverted, underscoring the importance of understanding the underlying causes. However, analyzing revert causes directly from transaction input data poses challenges, especially when the victim’s contract is not opensource. To address this challenge, we introduce a novel frequent mining method to analyze the causes of honeypots. The recovery success rate reaches 82.39%. Based on the causes that lead to transaction reverts, we propose potential strategies to mitigate these security risks and validate them in a simulated environment.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
"Clumsiness is Love Itself": How Long-Distance Couples Experience, Envision, and Resist AI in Intimate Relationships
Long-distance relationships increasingly rely on AI support, yet how couples conceptualize AI’s appropriate role remains poorly understood. Through semi-structured interviews with 14 individuals in LDRs, we investigate how participants experience, envision, and negotiate boundaries around AI involvement. While participants envisioned AI with contextual intelligence and dyadic understanding, current systems fell short by lacking "warmth", displacing relational accountability, and optimizing for individual rather than shared outcomes. Paradoxically, AI’s "perfection" surfaced the value of visible effort and imperfection: as one participant put it, "clumsiness is love itself." Participants articulated what we term "relational sovereignty", a couple’s right to remain the primary authors of their emotional labor, distinguishing acceptable AI involvement ("post-hoc pattern highlighter") from unacceptable intrusion ("real-time decision-maker"). We contribute design principles shifting AI toward relationship-centered scaffolds that preserve the sovereign work of connecting.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open Access"Clumsiness is Love Itself": How Long-Distance Couples Experience, Envision, and Resist AI in Intimate Relationships
Long-distance relationships increasingly rely on AI support, yet how couples conceptualize AI’s appropriate role remains poorly understood. Through semi-structured interviews with 14 individuals in LDRs, we investigate how participants experience, envision, and negotiate boundaries around AI involvement. While participants envisioned AI with contextual intelligence and dyadic understanding, current systems fell short by lacking "warmth", displacing relational accountability, and optimizing for individual rather than shared outcomes. Paradoxically, AI’s "perfection" surfaced the value of visible effort and imperfection: as one participant put it, "clumsiness is love itself." Participants articulated what we term "relational sovereignty", a couple’s right to remain the primary authors of their emotional labor, distinguishing acceptable AI involvement ("post-hoc pattern highlighter") from unacceptable intrusion ("real-time decision-maker"). We contribute design principles shifting AI toward relationship-centered scaffolds that preserve the sovereign work of connecting.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3259-3271
MioHint: LLM-Assisted Request Mutation for Whitebox REST API Testing
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3259-3271
Open AccessMioHint: LLM-Assisted Request Mutation for Whitebox REST API Testing
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 79-91
ConfLogger: Enhance Systems' Configuration Diagnosability through Configuration Logging
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 79-91
Open AccessConfLogger: Enhance Systems' Configuration Diagnosability through Configuration Logging
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1726-1738
LogFold: Compressing Logs with Structured Tokens and Hybrid Encoding
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1726-1738
Open AccessLogFold: Compressing Logs with Structured Tokens and Hybrid Encoding
- 17 March 2026
- Published by Springer Nature in Automated Software Engineering
- Vol. 33 (2) , 62
UpgradeShield: Detecting logic-state in-consistencies in smart contract upgrades
- 17 March 2026
- Published by Springer Nature in Automated Software Engineering
- Vol. 33 (2) , 62
UpgradeShield: Detecting logic-state in-consistencies in smart contract upgrades