Page 298 - 《软件学报》2026年第4期

凌祥 等: RMDroid: 基于多模态融合学习的安卓恶意软件鲁棒检测 1739

Foundations, Frontiers, and Applications. Singapore: Springer, 2022. 277–295. [doi: 10.1007/978-981-16-6054-2_13]
[65] Hamilton WL, Ying R, Leskovec J. Inductive representation learning on large graphs. In: Proc. of the 31st Int’l Conf. on Neural
Information Processing Systems. Long Beach: Curran Associates Inc., 2017. 1025–1035.
[66] Konstantinos P. Multimodal deep learning: Definition, examples, applications. 2022. https://www.v7labs.com/blog/multimodal-deep-
learning-guide
[67] Yang K, Lin WY, Barman M, Condessa F, Kolter Z. Defending multimodal fusion models against single-source adversaries. In: Proc. of
the 2021 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR). Nashville: IEEE, 2021. 3339–3348. [doi: 10.1109/
CVPR46437.2021.00335]
[68] Shazeer N, Mirhoseini A, Maziarz K, Davis A, Le Q, Hinton G, Dean J. Outrageously large neural networks: The sparsely-gated mixture-
of-experts layer. arXiv:1701.06538, 2017.
[69] Allix K, Bissyandé TF, Klein J, Le Traon Y. AndroZoo: Collecting millions of Android apps for the research community. In: Proc. of the
13th Int’l Conf. on Mining Software Repositories. Austin: ACM, 2016. 468–471. [doi: 10.1145/2901739.2903508]
[70] Daoudi N, Allix K, Bissyandé TF, Klein J. Assessing the opportunity of combining state-of-the-art Android malware detectors. Empirical
Software Engineering, 2023, 28(2): 22. [doi: 10.1007/S10664-022-10249-9]
[71] Wu YF, Shi J, Wang PC, Zeng DR, Sun C. DeepCatra: Learning flow- and graph-based behaviours for Android malware detection. IET
Information Security, 2023, 17(1): 118–130. [doi: 10.1049/ise2.12082]
[72] Lu J, Liu AJ, Dong F, Gu F, Gama J, Zhang GQ. Learning under concept drift: A review. IEEE Trans. on Knowledge and Data
Engineering, 2019, 31(12): 2346–2363. [doi: 10.1109/TKDE.2018.2876857]
[73] Khormali A, Abusnaina A, Chen SQ, Nyang D, Mohaisen A. COPYCAT: Practical adversarial attacks on visualization-based malware
detection. arXiv:1909.09735, 2019.
[74] Rosenberg I, Shabtai A, Rokach L, Elovici Y. Generic black-box end-to-end attack against state of the art API call based malware
classifiers. In: Bailey M, Holz T, Stamatogiannakis M, Ioannidis S, eds. Proc. of the 21st Int’l Symp. on Research in Attacks, Intrusions,
and Defenses. Heraklion: Springer, 2018. 490–510. [doi: 10.1007/978-3-030-00470-5_23]
[75] Desnos A. Androguard documentation. 2019. https://androguard.readthedocs.io/en/latest/index.html

附中文参考文献
[2] 雪豹财经社. 机构: 2023 年全球智能手机销量将同比下降 5%, 安卓份额约为 80%. 2023. https://www.speed-daily.com/newsflashes.
html#23981
[8] Tencent Inc. 腾讯手机管家. 2025. https://m.qq.com/
[9] Qihoo 360 Inc. 360 手机卫士 9.0. 2025. https://shouji.360.cn/v6/index.html
[15] 潘文雯, 王新宇, 宋明黎, 陈纯. 对抗样本生成技术综述. 软件学报, 2020, 31(1): 67–81. http://www.jos.org.cn/1000-9825/5884.htm
[doi: 10.13328/j.cnki.jos.005884]
[20] 汪嘉来, 张超, 戚旭衍, 荣易. Windows 平台恶意软件智能检测综述. 计算机研究与发展, 2021, 58(5): 977–994. [doi: 10.7544/issn
1000-1239.2021.20200964]
[21] 王时予. 基于多模态融合学习的安卓恶意软件鲁棒检测方法研究 [硕士学位论文]. 北京: 中国科学院大学, 2023.
[26] 维基百科. APK. 2025. https://zh.wikipedia.org/wiki/APK
[27] 李嬿婌. 移动终端侧的恶意软件检测. 2022. https://www.51cto.com/article/720959.html
[34] 凌祥, 纪守领, 任奎. 面向深度学习系统的对抗样本攻击与防御. 中国计算机学会通讯, 2018, 14(6): 11–17.

作者简介
凌祥, 博士, 副研究员, CCF 高级会员, 主要研究领域为智能软硬件安全, 人工智能安全.
周伯霖, 硕士, 主要研究领域为智能软件安全, 软件供应链安全.
王时予, 硕士, 主要研究领域为机器学习, 软件安全, 恶意软件检测.
罗天悦, 工程师, CCF 专业会员, 主要研究领域为操作系统安全分析, 代码漏洞挖掘, 人工智能安全.
尹鹏, 博士, 副研究员, 主要研究领域为网络安全, 设备安全检测.
吴春明, 博士, 教授, 博士生导师, CCF 专业会员, 主要研究领域为互联网体系架构, 可编程网络, 网络空间内生安全.
王滨, 博士, 研究员, 博士生导师, CCF 高级会员, 主要研究领域为人工智能安全, 物联网安全, 密码学.
吴敬征, 博士, 研究员, 博士生导师, CCF 杰出会员, 主要研究领域为系统安全, 漏洞挖掘, 操作系统安全.