Page 233 - 《软件学报》2026年第3期

1196 软件学报 2026 年第 37 卷第 3 期

[95] Allamanis M, Jackson-Flux H, Brockschmidt M. Self-supervised bug detection and repair. In: Proc. of the 35th Int’l Conf. on Neural
Information Processing Systems. Curran Associates Inc., 2021. 27865–27876.
[96] Li Z, Zhang C, Pan MX, Zhang T, Li XD. AACEGEN: Attention guided adversarial code example generation for deep code models. In:
Proc. of the 39th IEEE/ACM Int’l Conf. on Automated Software Engineering. Sacramento: ACM, 2024. 1245–1257. [doi: 10.1145/
3691620.3695500]
[97] Mi Q, Xiao Y, Cai Z, Jia XB. The effectiveness of data augmentation in code readability classification. Information and Software
Technology, 2021, 129: 106378. [doi: 10.1016/j.infsof.2020.106378]
[98] Zou J, Zhang SG, Qiu MK. Adversarial attacks on large language models. In: Proc. of the 17th Int’l Conf. on Knowledge Science,
Engineering and Management. Birmingham: Springer, 2024. 85–96. [doi: 10.1007/978-981-97-5501-1_7]
[99] Kumar P. Adversarial attacks and defenses for large language models (LLMs): Methods, frameworks & challenges. Int’l Journal of
Multimedia Information Retrieval, 2024, 13(3): 26. [doi: 10.1007/s13735-024-00334-8]
[100] Jain N, Schwarzschild A, Wen YX, Somepalli G, Kirchenbauer J, Chiang PY, Goldblum M, Saha A, Geiping J, Goldstein T. Baseline
defenses for adversarial attacks against aligned language models. arXiv:2309.00614, 2023.
[101] Robey A, Wong E, Hassani H, Pappas GJ. SmoothlLM: Defending large language models against jailbreaking attacks. arXiv:2310.
03684, 2023.
[102] Kumar A, Agarwal C, Srinivas S, Li AJ, Feizi S, Lakkaraju H. Certifying LLM safety against adversarial prompting. arXiv:2309.02705,
2023.
[103] Sheshadri A, Ewart A, Guo P, Lynch A, Wu C, Hebbar V, Sleight H, Stickland AC, Perez E, Hadfield-Menell D, Casper S. Latent
adversarial training improves robustness to persistent harmful behaviors in LLMs. arXiv:2407.15549, 2024.
[104] Lin G, Zhao QB. Large language model sentinel: Advancing adversarial robustness by LLM agent. arXiv:2405.20770, 2024.
[105] Xiao Y, Beschastnikh I, Rosenblum DS, Sun CS, Elbaum S, Lin Y, Dong JS. Self-checking deep neural networks in deployment. In:
Proc. of the 43rd IEEE/ACM Int’l Conf. on Software Engineering. Madrid: IEEE, 2021. 372–384. [doi: 10.1109/ICSE43902.2021.
00044]
[106] Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: Visual explanations from deep networks via gradient-
based localization. In: Proc. of the 2017 IEEE Int’l Conf. on Computer Vision. Venice: IEEE, 2017. 618–626. [doi: 10.1109/ICCV.
2017.74]

附中文参考文献
[4] 王赞, 闫明, 刘爽, 陈俊洁, 张栋迪, 吴卓, 陈翔. 深度神经网络测试研究综述. 软件学报, 2020, 31(5): 1255–1275. http://www.jos.org.
cn/1000-9825/5951.htm [doi: 10.13328/j.cnki.jos.005951]
[17] 曹雪洁, 陈俊洁, 闫明, 尤翰墨, 吴卓, 王赞. 基于数据变异的神经网络测试用例选择方法. 软件学报, 2024, 35(11): 4973–4992. http://
www.jos.org.cn/1000-9825/7005.htm [doi: 10.13328/j.cnki.jos.007005]

作者简介
田朝, 博士生, 主要研究领域为软件测试.
邝仕琦, 本科生, 主要研究领域为代码大模型测试与增强.
闫明, 博士生, 主要研究领域为深度学习系统测试, 芯片设计程序测试.
王海弛, 博士生, 主要研究领域为系统软件测试.
陈俊洁, 博士, 教授, 博士生导师, CCF 高级会员, 主要研究领域为软件分析与测试.