Page 230 - 《软件学报》2026年第3期

田朝 等: CoDefense: 面向对抗性攻击的多粒度代码归一化防御方法 1193

Association for Computational Linguistics. ACL, 2020. 7871–7880. [doi: 10.18653/v1/2020.acl-main.703]
[27] Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou YQ, Li W, Liu PJ. Exploring the limits of transfer learning with a
unified text-to-text Transformer. The Journal of Machine Learning Research, 2020, 21(1): 140.
[28] Wang SQ, Li Z, Qian HF, Yang CH, Wang ZJ, Shang MY, Kumar V, Tan S, Ray B, Bhatia P, Nallapati R, Ramanathan MK, Roth D,
Xiang B. Recode: Robustness evaluation of code generation models. In: Proc. of the 61st Annual Meeting of the Association for
Computational Linguistics. Toronto: ACL, 2022. 13818–13843. [doi: 10.18653/v1/2023.acl-long.773]
[29] Karampatsis RM, Babii H, Robbes R, Sutton C, Janes A. Big code != big vocabulary: Open-vocabulary models for source code. In:
Proc. of the 42nd ACM/IEEE Int’l Conf. on Software Engineering. Seoul: ACM, 2020. 1073–1085. [doi: 10.1145/3377811.3380342]
[30] Yefet N, Alon U, Yahav E. Adversarial examples for models of code. Proc. of the ACM on Programming Languages, 2020,
4(OOPSLA): 162. [doi: 10.1145/3428230]
[31] Tian Z, Chen JJ, Zhang XY. On-the-fly improving performance of deep code models via input denoising. In: Proc. of the 38th
IEEE/ACM Int’l Conf. on Automated Software Engineering. Luxembourg: IEEE, 2023. 560–572. [doi: 10.1109/ASE56229.2023.00166]
[32] Brown WH, Malveau RC, McCormick HWS, Mowbray TJ. AntiPatterns: Refactoring Software, Architectures, and Projects in Crisis.
New York: John Wiley & Sons, Inc., 1998.
[33] Mantyla M, Vanhanen J, Lassenius C. A taxonomy and an initial empirical study of bad smells in code. In: Proc. of the 2003 Int’l Conf.
on Software Maintenance. Amsterdam: IEEE, 2003. 381–384. [doi: 10.1109/ICSM.2003.1235447]
[34] Wake WC. Refactoring Workbook. Boston: Addison-Wesley Longman, 2003.
[35] Martin RC. Clean code: A Handbook of Agile Software Craftsmanship. Upper Saddle River: Pearson, 2008.
[36] Romano S, Vendome C, Scanniello G, Poshyvanyk D. A multi-study investigation into dead code. IEEE Trans. on Software
Engineering, 2020, 46(1): 71–99. [doi: 10.1109/TSE.2018.2842781]
[37] Nguyen TD, Zhou Y, Le XBD, Thongtanunam P, Lo D. Adversarial attacks on code models with discriminative graph patterns.
arXiv:2308.11161, 2023.
[38] Bui NDQ, Yu YJ, Jiang LX. Self-supervised contrastive learning for code retrieval and summarization via semantic-preserving
transformations. In: Proc. of the 44th Int’l ACM SIGIR Conf. on Research and Development in Information Retrieval. ACM, 2021.
511–521. [doi: 10.1145/3404835.3462840]
[39] Srikant S, Liu SJ, Mitrovska T, Chang SY, Fan QF, Zhang GY, O’Reilly UM. Generating adversarial computer programs using
optimized obfuscations. arXiv:2103.11882, 2021.
[40] Jia JH, Srikant S, Mitrovska T, Gan C, Chang SY, Liu SJ. ClawSAT: Towards both robust and accurate code models. In: Proc. of the
2023 IEEE Int’l Conf. on Software Analysis, Evolution and Reengineering. Macao: IEEE, 2023. 212–223. [doi: 10.1109/SANER56733.
2023.00029]
[41] Li J, Li Z, Zhang HZ, Li G, Jin Z, Hu X, Xia X. Poison attack and defense on deep source code processing models. arXiv:2210.17029, 2022.
[42] Bielik P, Vechev M. Adversarial robustness for code. In: Proc. of the 37th Int’l Conf. on Machine Learning. JMLR.org, 2020. 896–907.
[doi: 10.48550/arXiv.2002.04694]
[43] Zhuo TY, Yang Z, Sun ZS, Wang YF, Li L, Du XN, Xing ZC, Lo D. Data augmentation approaches for source code models: A survey.
arXiv:2305.19915, 2023.
[44] Mercuri V, Saletta M, Ferretti C. Evolutionary approaches for adversarial attacks on neural source code classifiers. Algorithms, 2023,
16(10): 478. [doi: 10.3390/a16100478]
[45] Henkel J, Ramakrishnan G, Wang Z, Albarghouthi A, Jha S, Reps T. Semantic robustness of models of source code. In: Proc. of the
2022 IEEE Int’l Conf. on Software Analysis, Evolution and Reengineering. Honolulu: IEEE, 2022. 526–537. [doi: 10.1109/
SANER53432.2022.00070]
[46] Gopstein D, Iannacone J, Yan Y, DeLong L, Zhuang YY, Yeh MKC, Cappos J. Understanding misunderstandings in source code. In:
Proc. of the 11th Joint Meeting on Foundations of Software Engineering. Paderborn: ACM, 2017. 129–139. [doi: 10.1145/3106237.
3106264]
[47] Li Z, Chen GQ, Chen C, Zou YY, Xu SH. RoPGen: Towards robust code authorship attribution via automatic coding style
transformation. In: Proc. of the 44th IEEE/ACM Int’l Conf. on Software Engineering. Pittsburgh: IEEE, 2022. 1906–1918. [doi: 10.1145/
3510003.3510181]
[48] Chakraborty S, Ahmed T, Ding Y, Devanbu PT, Ray B. Natgen: Generative pre-training by “naturalizing” source code. In: Proc. of the
30th ACM Joint European Software Engineering Conf. and Symp. on the Foundations of Software Engineering. Singapore: ACM, 2022.
18–30. [doi: 10.1145/3540250.3549162]
[49] Li Z, Zhang RQ, Zou DQ, Wang N, Li YT, Xu SH. Robin: A novel method to produce robust interpreters for deep learning-based code