Page 358 - 《软件学报》2025年第9期

赵亚茹 等: 云边联邦学习系统下抗投毒攻击的防御方法 4269

Trans. on Computational Social Systems, 2020, 7(3): 818–826. [doi: 10.1109/TCSS.2019.2960824]
[19] Cao XY, Zhang ZX, Jia JY, Gong NZ. FLCert: Provably secure federated learning against poisoning attacks. IEEE Trans. on Information
Forensics and Security, 2022, 17: 3691–3705. [doi: 10.1109/TIFS.2022.3212174]
[20] Ma ZR, Ma JF, Miao YB, Li YJ, Deng RH. ShieldFL: Mitigating model poisoning attacks in privacy-preserving federated learning. IEEE
Trans. on Information Forensics and Security, 2022, 17: 1639–1654. [doi: 10.1109/TIFS.2022.3169918]
[21] Shi ZS, Ding XY, Li FG, Chen YN, Li CR. Mitigation of poisoning attack in federated learning by using historical distance detection. In:
Proc. of the 5th Cyber Security in Networking Conf. (CSNet). Abu Dhabi: IEEE, 2021. 10–17. [doi: 10.1109/CSNet52717.2021.9614278]
[22] Zhao YR, Zhang JB, Cao YH. Manipulating vulnerability: Poisoning attacks and countermeasures in federated cloud-edge-client learning
for image classification. Knowledge-based Systems, 2023, 259: 110072. [doi: 10.1016/j.knosys.2022.110072]
[23] Al-Maslamani NM, Ciftler BS, Abdallah M, Mahmoud MMEA. Toward secure federated learning for IoT using DRL-enabled reputation
mechanism. IEEE Internet of Things Journal, 2022, 9(21): 21971–21983. [doi: 10.1109/JIOT.2022.3184812]
[24] Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G, Petersen S,
Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D. Human-level control through deep
reinforcement learning. Nature, 2015, 518(7540): 529–533. [doi: 10.1038/nature14236]
[25] Liu YN, Li KQ, Jin YW, Zhang Y, Qu WY. A novel reputation computation model based on subjective logic for mobile ad hoc networks.
Future Generation Computer Systems, 2011, 27(5): 547–554. [doi: 10.1016/j.future.2010.03.006]
[26] Wang WX, Levine A, Feizi S. Improved certified defenses against data poisoning with (deterministic) finite aggregation. arXiv:
2202.02628, 2022.
[27] Mozaffari H, Shejwalkar V, Houmansadr A. Every vote counts: Ranking-based training of federated learning to resist poisoning attacks.
In: Proc. of the 32nd USENIX Conf. on Security Symp. Anaheim: USENIX Association, 2023. 1721–1738.
[28] Zhang JL, Chen JJ, Wu D, Chen B, Yu S. Poisoning attack in federated learning using generative adversarial nets. In: Proc. of the 18th
IEEE Int’l Conf. on Trust, Security and Privacy in Computing and Communications and the 13th IEEE Int’l Conf. on Big Data Science
and Engineering (TrustCom/BigDataSE). Rotorua: IEEE, 2019. 374–380. [doi: 10.1109/TrustCom/BigDataSE.2019.00057]
[29] Zhao Y, Chen JJ, Zhang JL, Wu D, Blumenstein M, Yu S. Detecting and mitigating poisoning attacks in federated learning using
generative adversarial networks. Concurrency and Computation: Practice and Experience, 2022, 34(7): e5906. [doi: 10.1002/cpe.5906]
[30] Liu XY, Li HW, Xu GW, Chen ZQ, Huang XM, Lu RX. Privacy-enhanced federated learning against poisoning adversaries. IEEE Trans.
on Information Forensics and Security, 2021, 16: 4574–4588. [doi: 10.1109/TIFS.2021.3108434]
[31] Tolpegin V, Truex S, Gursoy ME, Liu L. Data poisoning attacks against federated learning systems. In: Proc. of the 25th European Symp.
on Research in Computer Security. Guildford: Springer, 2020. 480–501. [doi: 10.1007/978-3-030-58951-6_24]
[32] Fraboni Y, Vidal R, Lorenzi M. Free-rider attacks on model aggregation in federated learning. In: Proc. of the 24th Int’l Conf. on
Artificial Intelligence and Statistics. San Diego: PMLR, 2021. 1846–1854.
[33] Fung C, Yoon CJM, Beschastnikh I. Mitigating sybils in federated learning poisoning. arXiv:1808.04866, 2020.
[34] Jagielski M, Oprea A, Biggio B, Liu C, Nita-Rotaru C, Li B. Manipulating machine learning: Poisoning attacks and countermeasures for
regression learning. In: Proc. of the 2018 IEEE Symp. on Security and Privacy (SP). San Francisco: IEEE, 2018. 19–35. [doi: 10.1109/SP.
2018.00057]
[35] Jebreel NM, Domingo-Ferrer J. FL-Defender: Combating targeted attacks in federated learning. Knowledge-based Systems, 2023, 260:
110178. [doi: 10.1016/j.knosys.2022.110178]
[36] Sharipuddin, Purnama B, Kurniabudi, Winanto EA, Stiawan D, Hanapi D, Idris MYB, Budiarto R. Features extraction on IoT intrusion
detection system using principal components analysis (PCA). In: Proc. of the 7th Int’l Conf. on Electrical Engineering, Computer
Sciences and Informatics. Yogyakarta: IEEE, 2020. 114–118. [doi: 10.23919/EECSI50503.2020.9251292]
[37] Zhao YR, Cao YH, Zhang JB, Huang HX, Liu YH. FlexibleFL: Mitigating poisoning attacks with contributions in cloud-edge federated
learning systems. Information Sciences, 2024, 664: 120350. [doi: 10.1016/j.ins.2024.120350]
[38] Ramanujan V, Wortsman M, Kembhavi A, Farhadi A, Rastegari M. What’s hidden in a randomly weighted neural network? In: Proc. of
the 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR). Seattle: IEEE, 2020. 11890–11899. [doi: 10.1109/
CVPR42600.2020.01191]
[39] He KM, Zhang XY, Ren SQ, Sun J. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. In:
Proc. of the 2015 IEEE Int’l Conf. on Computer Vision. Santiago: IEEE, 2015. 1026–1034. [doi: 10.1109/ICCV.2015.123]
[40] Li XY, Qu Z, Zhao SQ, Tang B, Lu Z, Liu Y. LoMar: A local defense against poisoning attack on federated learning. IEEE Trans. on
Dependable and Secure Computing, 2023, 20(1): 437–450. [doi: 10.1109/TDSC.2021.3135422]
[41] Lyu L, Xu XY, Wang Q, Yu H. Collaborative fairness in federated learning. In: Yang Q, Fan LX, Yu H, eds. Federated Learning: Privacy