[1] 王人帅, 杨奎武, 陈越, 等. 面向图像数据的深度学习后门攻击技术综述[J]. 计算机工程, 2026, 52(3): 62-78. DOI: 10.19678/j.issn.1000-3428.0070128.
WANG Renshuai, YANG Kuiwu, CHEN Yue, et al. Survey of Deep Learning Backdoor Attack on Image Data[J]. Computer Engineering, 2026, 52(3): 62-78. DOI: 10.19678/j.issn.1000-3428.0070128. (in Chinese)
[2] GU T Y, DOLAN-GAVITT B, GARG S. BadNets: identifying vulnerabilities in the machine learning model supply chain[EB/OL]. 2017: arXiv:1708.06733.
[3] CHEN X Y, LIU C, LI B, et al. Targeted backdoor attacks on deep learning systems using data poisoning[EB/OL]. 2017: arXiv:1712.05526.
[4] BARNI M, KALLAS K, TONDI B. A new backdoor attack in CNNs by training set corruption without label poisoning[C]//Proceedings of the IEEE International Conference on Image Processing. Piscataway: IEEE, 2019: 101-105.
[5] WANG T, YAO Y, XU F, et al. An invisible black-box backdoor attack through frequency domain [C]//Proceedings of the European Conference on Computer Vision. Cham: Springer, 2022: 396-413. DOI: 10.1007/978-3-031-19778-9_23.
[6] ZENG Y, PARK W, MAO Z M, et al. Rethinking the backdoor attacks' triggers: a frequency perspective[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 16453-16461.
[7] GAO Y D, CHEN H L, SUN P, et al. A dual stealthy backdoor: from both spatial and frequency perspectives[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2024: 1851-1859.
[8] LI S F, XUE M H, ZHAO B, et al. Invisible backdoor attacks on deep neural networks via steganography and regularization[J]. IEEE Transactions on Dependable and Secure Computing, 2021, 18(5): 2088-2105.
[9] LUO Z Y, LI F X, PENG J. LBP-LSB co-optimisation for dynamic unseen backdoor attacks[J]. Electronics, 2025, 14(21): 4216.
[10] CHEN B, CARVALHO W, BARACALDO N, et al. Detecting backdoor attacks on deep neural networks by activation clustering[EB/OL]. (2018-11-09)[2026-07-24]. https://arxiv.org/abs/1811.03728.
[11] TRAN B, LI J, MADRY A. Spectral signatures in backdoor attacks[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook: Curran Associates, 2018: 8011-8021.
[12] HAYASE J, KONG W, SOMANI R, et al. SPECTRE: defending against backdoor attacks using robust statistics[C]//Proceedings of the 38th International Conference on Machine Learning. PMLR, 2021: 4129-4139.
[13] MA W L, WANG D R, SUN R X, et al. The Beatrix resurrections: robust backdoor detection via Gram matrices[C]//Proceedings of the Network and Distributed System Security Symposium. San Diego: Internet Society, 2023.
[14] GAO Y S, XU C, WANG D R, et al. STRIP: a defence against Trojan attacks on deep neural networks[C]//Proceedings of the Annual Computer Security Applications Conference. New York: ACM, 2019: 113-125. DOI: 10.1145/3359789.3359790.
[15] PAN M Z, ZENG Y, LYU L J, et al. ASSET: robust backdoor data detection across a multiplicity of deep learning paradigms[C]//Proceedings of the 32nd USENIX Security Symposium. Anaheim: USENIX Association, 2023: 2725-2742.
[16] CHOU E, TRAMER F, PELLEGRINO G. SentiNet: detecting localized universal attacks against deep learning systems[C]//Proceedings of the IEEE Security and Privacy Workshops. Piscataway: IEEE, 2020: 48-54.
[17] DOAN B G, ABBASNEJAD E, RANASINGHE D C. Februus: input purification defense against Trojan attacks on deep neural network systems[C]//Proceedings of the Annual Computer Security Applications Conference. New York: ACM, 2020: 897-912.
[18] LI Y G, LYU X X, KOREN N, et al. Anti-backdoor learning: training clean models on poisoned data[C]//Proceedings of the 35th Conference on Neural Information Processing Systems. Red Hook: Curran Associates, 2021: 14900-14912.
[19] HUANG K Z, LI Y M, WU B Y, et al. Backdoor defense via decoupling the training process[C]//Proceedings of the 10th International Conference on Learning Representations. 2022.
[20] GAO K F, BAI Y, GU J D, et al. Backdoor defense via adaptively splitting poisoned dataset[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 4005-4014.
[21] LI Y M, JIANG Y, LI Z F, et al. Backdoor learning: a survey[J]. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(1): 5-22. DOI: 10.1109/TNNLS.2022.3182979.
[22] 江钦辉, 李默涵, 孙彦斌. 深度神经网络后门防御综述[J]. 信息安全学报, 2024, 9(4): 47-63. DOI: 10.19363/J.cnki.cn10-1380/tn.2024.07.03.
JIANG Qinhui, LI Mohan, SUN Yanbin. A Survey on Defense against Deep Neural Network Backdoor Attack[J]. Journal of Cyber Security, 2024, 9(4): 47-63. DOI: 10.19363/J.cnki.cn10-1380/tn.2024.07.03. (in Chinese)
[23] OJALA T, PIETIKAINEN M, MAENPAA T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002,24(7): 971-987. DOI: 10.1109/TPAMI.2002.1017623.
[24] FRIDRICH J, GOLJAN M, DU R. Detecting LSB steganography in color and gray-scale images[J]. IEEE MultiMedia, 2001, 8(4): 22-28. DOI: 10.1109/93.959097.
[25] 曾嘉忻, 张卫明, 张荣. 基于后门的鲁棒后向模型水印方法[J]. 计算机工程, 2024, 50(2): 132-139. DOI: 10.19678/j.issn.1000-3428.0067063.
ZENG Jiaxin, ZHANG Weiming, ZHANG Rong. Robust Backward Model Watermarking Method Based on Backdoor[J]. Computer Engineering, 2024, 50(2): 132-139. DOI: 10.19678/j.issn.1000-3428.0067063. (in Chinese)
[26] LI W, CHEN P Y, LIU S, et al. PSBD: prediction shift uncertainty unlocks backdoor detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2025: 10255-10264. DOI: 10.1109/CVPR52734.2025.00959.
[27] TANG S, ZHANG Z, PAN J, et al. AFI: blackbox backdoor detection method based on adaptive feature injection[J]. Computers, Materials & Continua,2026,87(1):1-10. DOI: 10.32604/cmc.2025.073798.
[28] CHEN J, ZHOU S, ZHANG L, et al. Disentangling malicious memorization: inference-time backdoor samples detection via self-influence functions[J]. Concurrency and Computation: Practice and Experience, 2026, 38(9): e70747. DOI: 10.1002/cpe.70747.
[29] SCHOLKOPF B, PLATT J C, SHAWE-TAYLOR J, et al. Estimating the support of a high-dimensional distribution[J]. Neural Computation, 2001, 13(7): 1443-1471.
[30] TAX D M J, DUIN R P W. Support vector data description[J]. Machine Learning, 2004, 54(1): 45-66.
[31] KRIZHEVSKY A. Learning multiple layers of features from tiny images[R/OL]. Toronto: University of Toronto, 2009[2026-07-24]. https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf.
[32] LE Y, YANG X. Tiny ImageNet visual recognition challenge[R/OL]. Stanford: Stanford University, 2015[2026-07-24]. https://cs231n.stanford.edu/reports/2015/pdfs/yle_project.pdf.
[33] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778.
[34] HOU L S, FENG R L, HUA Z Y, et al. IBD-PSC: input-level backdoor detection via parameter-oriented scaling consistency[C]//Proceedings of the 41st International Conference on Machine Learning. PMLR, 2024, 235: 18992-19022.
|