Page 147 - 《软件学报》2026年第4期

1588 软件学报 2026 年第 37 卷第 4 期

[30] Long S, Tao W, Zhang ZD, Tao Q. Adaptive NAG methods based on AdaGrad and its optimal individual convergence. Ruan Jian Xue
Bao/Journal of Software, 2022, 33(4): 1231–1243 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6464.htm [doi: 10.
13328/j.cnki.jos.006464]
[31] Xie XY, Zhou P, Li H, Lin ZC, Yan SC. Adan: Adaptive nesterov momentum algorithm for faster optimizing deep models. IEEE Trans.
on Pattern Analysis and Machine Intelligence, 2024, 46(12): 9508–9520. [doi: 10.1109/TPAMI.2024.3423382]
[32] Lin JD, Song CB, He K, Wang LW, Hopcroft JE. Nesterov accelerated gradient and scale invariance for adversarial attacks. In: Proc. of
the 2020 Int’l Conf. on Learning Representations. OpenReview.net. 2020.
[33] Zou JH, Duan YX, Ren CL, Qiu JY, Zhou XY, Pan ZS. Perturbation initialization, Adam-Nesterov and quasi-hyperbolic momentum for
adversarial examples. Acta Electronica Sinica, 2022, 50(1): 207–216 (in Chinese with English abstract). [doi: 10.12263/DZXB.20200839]
[34] Bao L, Tao W, Tao Q. Boosting adversarial transferability through adaptive-learning-rate with data augmentation mechanism. Acta
Electronica Sinica, 2024, 52(1): 157–169 (in Chinese with English abstract). [doi: 10.12263/DZXB.20220737]
[35] Shafahi A, Najibi M, Ghiasi M, Xu Z, Dickerson J, Studer C, Davis LS, Taylor G, Goldstein T. Adversarial training for free! In: Proc. of
the 33rd Int’l Conf. on Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2019. 3358–3369.
[36] Wong E, Rice L, Kolter JZ. FAST is better than free: Revisiting adversarial training. In: Proc. of the 2020 Int’l Conf. on Learning
Representations. OpenReview.net. 2020.
[37] Jia XJ, Zhang Y, Wei XX, Wu BY, Ma K, Wang J, Cao XC. Prior-guided adversarial initialization for fast adversarial training. In: Avidan
S, Brostow G, Cissé M, Farinella GM, Hassner T, eds. Proc. of the 17th European Conf. on Computer Vision (ECCV). Tel Aviv:
Springer, 2022. 567–584. [doi: 10.1007/978-3-031-19772-7_33]
[38] Jia XJ, Zhang Y, Wei XX, Wu BY, Ma K, Wang J, Cao XC. Improving fast adversarial training with prior-guided knowledge. IEEE
Trans. on Pattern Analysis and Machine Intelligence, 2024, 46(9): 6367–6383. [doi: 10.1109/TPAMI.2024.3381180]
[39] Nesterov Y. Introductory Lectures on Convex Optimization—A Basic Course. New York: Springer, 2004. 1–236. [doi: 10.1007/978-1-
4419-8853-9]
[40] Ghadimi S, Lan GH. Accelerated gradient methods for nonconvex nonlinear and stochastic programming. Mathematical Programming,
2016, 156(1–2): 59–99. [doi: 10.1007/s10107-015-0871-8]
[41] Everingham M, Eslami SMA, van Gool L, Williams CKI, Winn J, Zisserman A. The PASCAL visual object classes challenge: A
retrospective. Int’l Journal of Computer Vision, 2015, 111(1): 98–136. [doi: 10.1007/s11263-014-0733-5]
[42] Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P, Zitnick CL. Microsoft COCO: Common objects in context. In:
Fleet D, Pajdla T, Schiele B, Tuytelaars T, eds. Proc. of the 13th European Conf. on Computer Vision (ECCV). Zurich: Springer, 2014.
740–755. [doi: 10.1007/978-3-319-10602-1_48]

附中文参考文献
[8] 王璐瑶, 曹渊, 刘博涵, 曾恩, 刘坤, 夏元清. 时间序列分类模型的集成对抗训练防御方法. 自动化学报, 2025, 51(1): 144–160. [doi:
10.16383/j.aas.c240050]
[16] 王生生, 路淑贞, 曹斌. 面向隐私保护联邦学习的医学影像目标检测算法. 计算机辅助设计与图形学学报, 2021, 33(10): 1553–1562.
[doi: 10.3724/SP.J.1089.2021.18416]
[24] 陆宇轩, 刘泽禹, 罗咏刚, 邓森友, 江天, 马金燕, 董胤蓬. 基于生成对抗网络的目标检测黑盒迁移攻击算法. 软件学报, 2024, 35(7):
3531–3550. http://www.jos.org.cn/1000-9825/6937.htm [doi: 10.13328/j.cnki.jos.006937]
[25] 汪欣欣, 陈晶, 何琨, 张子君, 杜瑞颖, 李瞧, 佘计思. 面向目标检测的对抗攻击与防御综述. 通信学报, 2023, 44(11): 260–277. [doi:
10.11959/j.issn.1000-436x.2023223]
[30] 陇盛, 陶蔚, 张泽东, 陶卿. 基于 AdaGrad 的自适应 NAG 方法及其最优个体收敛性. 软件学报, 2022, 33(4): 1231–1243. http://www.
jos.org.cn/1000-9825/6464.htm [doi: 10.13328/j.cnki.jos.006464]
[33] 邹军华, 段晔鑫, 任传伦, 邱俊洋, 周星宇, 潘志松. 基于噪声初始化、Adam-Nesterov 方法和准双曲动量方法的对抗样本生成方法.
电子学报, 2022, 50(1): 207–216. [doi: 10.12263/DZXB.20200839]
[34] 鲍蕾, 陶蔚, 陶卿. 结合自适应步长策略和数据增强机制提升对抗攻击迁移性. 电子学报, 2024, 52(1): 157–169. [doi: 10.12263/
DZXB.20220737]

附录 A. 定理 1 证明

d
若 S x = R , 那么有: