自动化学报2026，Vol.52Issue(4)：638-665,28.DOI:10.16383/j.aas.c250331
源代码处理任务中的深度学习模型对抗攻防研究综述
Survey on Adversarial Attack and Defense Methods for Deep Learning Models in Source Code Processing Tasks
摘要
Abstract
With the development of intelligent software,the application of deep learning models in source code pro-cessing tasks,such as defect detection and localization,has become increasingly widespread.But their lack of ro-bustness has also become increasingly evident.Many researchers have conducted in-depth studies on adversarial at-tack and defense methods for source code.However,existing surveys rarely summarize model characteristics from the perspective of source code task-specific properties,and there is a lack of systematic review and analysis of typic-al adversarial attack and defense methods such as model stealing,backdoor defense,and defensive distillation.Firstly,from the perspective of model architecture,we systematically outline deep learning models for source code processing tasks,and analyze their performance and adaptability under adversarial attack environments.Sub-sequently,we conduct a comprehensive review and classification of adversarial attack and defense methods for source code,and summarize the relevant benchmark datasets.Finally,we analyze the limitations of existing re-search and propose potential directions for future research.关键词
深度学习/源代码处理/对抗攻防方法/鲁棒性Key words
deep learning/source code processing/adversarial attack and defense methods/robustness引用本文复制引用
潘海为,马宝英,张可佳,杨晓阳,秦颖鑫,卢国强,范书平..源代码处理任务中的深度学习模型对抗攻防研究综述[J].自动化学报,2026,52(4):638-665,28.基金项目
黑龙江省重点研发计划(2024ZXDXA09),船舶 CAE 软件典型场景研究与应用项目(CBZ01N23-02),黑龙江省自然科学基金(PL2024F022)资助 Supported by Key Research and Development Program of Hei-longjiang Province(2024ZXDXA09),the Research and Applica-tion Project of Typical Scenarios for Ship CAE Software(CBZ01N23-02),and Natural Science Foundation of Heilongji-ang Province(PL2024F022) （2024ZXDXA09）
