Agent That Debugs: Dynamic State-Guided Vulnerability Repair
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912319573852160 |
|---|---|
| author | Liu, Zhengyao Ma, Yunlong Xu, Jingxuan Ai, Junchen Gao, Xiang Sun, Hailong Roychoudhury, Abhik |
| author_facet | Liu, Zhengyao Ma, Yunlong Xu, Jingxuan Ai, Junchen Gao, Xiang Sun, Hailong Roychoudhury, Abhik |
| contents | In recent years, more vulnerabilities have been discovered every day, while manual vulnerability repair requires specialized knowledge and is time-consuming. As a result, many detected or even published vulnerabilities remain unpatched, thereby increasing the exposure of software systems to attacks. Recent advancements in agents based on Large Language Models have demonstrated their increasing capabilities in code understanding and generation, which can be promising to achieve automated vulnerability repair. However, the effectiveness of agents based on static information retrieval is still not sufficient for patch generation. To address the challenge, we propose a program repair agent called VulDebugger that fully utilizes both static and dynamic context, and it debugs programs in a manner akin to humans. The agent inspects the actual state of the program via the debugger and infers expected states via constraints that need to be satisfied. By continuously comparing the actual state with the expected state, it deeply understands the root causes of the vulnerabilities and ultimately accomplishes repairs. We experimentally evaluated VulDebugger on 50 real-life projects. With 60.00% successfully fixed, VulDebugger significantly outperforms state-of-the-art approaches for vulnerability repair. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07634 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Agent That Debugs: Dynamic State-Guided Vulnerability Repair Liu, Zhengyao Ma, Yunlong Xu, Jingxuan Ai, Junchen Gao, Xiang Sun, Hailong Roychoudhury, Abhik Software Engineering In recent years, more vulnerabilities have been discovered every day, while manual vulnerability repair requires specialized knowledge and is time-consuming. As a result, many detected or even published vulnerabilities remain unpatched, thereby increasing the exposure of software systems to attacks. Recent advancements in agents based on Large Language Models have demonstrated their increasing capabilities in code understanding and generation, which can be promising to achieve automated vulnerability repair. However, the effectiveness of agents based on static information retrieval is still not sufficient for patch generation. To address the challenge, we propose a program repair agent called VulDebugger that fully utilizes both static and dynamic context, and it debugs programs in a manner akin to humans. The agent inspects the actual state of the program via the debugger and infers expected states via constraints that need to be satisfied. By continuously comparing the actual state with the expected state, it deeply understands the root causes of the vulnerabilities and ultimately accomplishes repairs. We experimentally evaluated VulDebugger on 50 real-life projects. With 60.00% successfully fixed, VulDebugger significantly outperforms state-of-the-art approaches for vulnerability repair. |
| title | Agent That Debugs: Dynamic State-Guided Vulnerability Repair |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2504.07634 |