Analysis on Security and Privacy-preserving in Federated Learning
DOI:
https://doi.org/10.54097/hset.v4i.923Keywords:
Federated Learning, Poisoning Attack, Adversarial Attack, Privacy Leakage, Privacy Policy.Abstract
Data privacy breaches during the training and implementation of the model are the main challenges that impede the development of artificial intelligence technologies today. Federated Learning has been an effective tool for the protection of privacy. Federated Learning is a distributive machine learning method that trains a non-destructive learning module based on a local training and passage of parameters from participants, with no required direct access to data source. Federated Learning still holds many pitfalls. This paper first introduces the types of federated learning, including horizontal federated learning, vertical federated learning and federated transfer learning, and then analyses the existing security risks of poisoning attacks, adversarial attacks and privacy leaks, with privacy leaks becoming a security risk that cannot be ignored at this stage. This paper also summarizes the corresponding defence measures, from three aspects: Poison attack defence, Privacy Leak Defence, and Defence against attack, respectively. This paper introduces the defence measures taken against some threats faced by federated learning, and finally gives some future research directions.
Downloads
References
H. B. Mcmahan, E. Moore, D. Ramage, et al.Federated learning of deep networks using model averaging[J]. arXiv preprint, arXiv: 1602.05629,2016.
J. Konečný, H. B. Mcmahan, D. Ramage,et al.Federated optimization:distributed machine learning for ondevice intelligence[J]. arXiv preprint, arXiv: 1610.02527, 2016.
J. Konečný, H. B. Mcmahan, YU F. X.,et al.Federated learning: Strategies for improving communication efficiency[J]. arXiv preprint, arXiv: 1610.05492,2016.
G. Sivek, M. Mohri, A. T. Suresh.Agnostic federated learning[J]. arXiv preprint, arXiv: 1902.00146,2019.
M. Yurochkin, M. Agarwal, S. Ghosh, et al. Bayesian nonparametric federated learning of neural networks[J]. arXiv preprint, arXiv: 1905.12022, 2019.
S. Niknam, H. S. Dhillon, J. H. Reed. Federated learning for wireless communications:Motivation, opportunities and challenges[J]. arXiv preprint, arXiv: 1908.06847, 2019.
G. A. Rena, M. J. Sheller, B. Edwards, et al. Multi-institutional deep learning modeling without sharingpatient data:A feasibility study on brain tumor segmentation[C]// International MICCAI Brainlesion Workshop. Springer, Cham.
Y. Chen, X. Qin, J. Wang, C. Yu and W. Gao, "FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare" in IEEE Intelligent Systems, vol. 35, no. 04, pp. 83-93, 2020.doi: 10.1109/MIS.2020.2988604
B. Hu, Design and implementation of air quality monitoring system based on federated learning[D]. Beijing: Beijing University of Posts and Telecommunications, 2019.
Custers, B., Sears, A. M., Dechesne, F., Georgieva, I., Tani, T., & Van der Hof, S. (2019). EU personal data protection in policy and practice. TMC Asser Press.
Asad, Muhammad & Moustafa, Ahmed & Yu, Chao. (2020). A Critical Evaluation of Privacy and Security Threats in Federated Learning. Sensors. 20. 7182. 10.3390/s20247182.
Pan S. J., Yang Q.. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2009, 22(10): 1345 − 1359.
X. Zhou, J. Men, G. Xu, Z. Han, Z. Sun, W. Lian, X. Cheng, Finding sands in the eyes: vulnerabilities discovery in IoT with EUFuzzer on human machine interface, IEEE Access 7 (2019) 103751–103759.
Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., & Shmatikov, V. (2020, June). How to backdoor federated learning. In International Conference on Artificial Intelligence and Statistics (pp. 2938-2948). PMLR.
Mothukuri, V., Parizi, R. M., Pouriyeh, S., Huang, Y., Dehghantanha, A., & Srivastava, G. (2021). A survey on security and privacy of federated learning. Future Generation Computer Systems, 115, 619-640.
G. Sun, Y. Cong, J. Dong, Q. Wang, L. Lyu and J. Liu, "Data Poisoning Attacks on Federated Machine Learning," in IEEE Internet of Things Journal, doi: 10.1109/JIOT.2021.3128646.
Abad, G., Paguada, S., Picek, S., Ramírez-Durán, V. J., & Urbieta, A. (2022). Client-Wise Targeted Backdoor in Federated Learning. arXiv preprint arXiv:2203.08689.
H., Liu, D., Li & Y., Li Poisonous Label Attack: Black-Box Data Poisoning Attack with Enhanced Conditional DCGAN. Neural Process Lett 53, 4117–4142 (2021).
Lim, W. Y. B., Luong, N. C., Hoang, D. T., Jiao, Y., Liang, Y. C., Yang, Q., ... & Miao, C. (2020). Federated learning in mobile edge networks: A comprehensive survey. IEEE Communications Surveys & Tutorials, 22(3), 2031-2063.
Bhagoji, A. N., Chakraborty, S., Mittal, P., & Calo, S. (2019, May). Analyzing federated learning through an adversarial lens. In International Conference on Machine Learning (pp. 634-643). PMLR.
He, Y. , Hu, X. , He, J. , Meng, G. , & Chen, K. . (2019). Privacy and security issues in machine learning systems: a survey. Journal of Computer Research and Development.
Tramèr, F., Zhang, F., Juels, A., Reiter, M. K., & Ristenpart, T. (2016). Stealing Machine Learning Models via Prediction {APIs}. In 25th USENIX security symposium (USENIX Security 16) (pp. 601-618).
L. V. Mancini, G. Ateniese, G. Felici, et al.Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers[J]. arX[1]iv preprint, arXiv: 1306.4447, 2013.
Qin, J., Liu, B., & Qian, J. (2021, January). A Novel Privacy-Preserved Recommender System Framework based on Federated Learning. In 2021 The 4th International Conference on Software Engineering and Information Management (pp. 82-88).
Li, X., Qu, Z., Zhao, S., Tang, B., Lu, Z., & Liu, Y. (2021). LoMar: A Local Defense Against Poisoning Attack on Federated Learning. IEEE Transactions on Dependable and Secure Computing.
Tian, Y., Zhang, W., Simpson, A., Liu, Y., & Jiang, Z. L. (2021). Defending Against Data Poisoning Attacks: From Distributed Learning to Federated Learning. The Computer Journal.
Tolpegin, V., Truex, S., Gursoy, M. E., & Liu, L. (2020, September). Data poisoning attacks against federated learning systems. In European Symposium on Research in Computer Security (pp. 480-501). Springer, Cham.
Geyer, R. C., Klein, T., & Nabi, M. (2017). Differentially private federated learning: A client level perspective. arXiv preprint arXiv:1712.07557.
Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., ... & Seth, K. (2017, October). Practical secure aggregation for privacy-preserving machine learning. In proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security (pp. 1175-1191).
Aono, Y., Hayashi, T., Wang, L., & Moriai, S. (2017). Privacy-preserving deep learning via additively homomorphic encryption. IEEE Transactions on Information Forensics and Security, 13(5), 1333-1345.
E. Hesamifard, H. Takabi, M. Ghasemi. Cryptodl: Deep neural networks over encrypted data[J]. arXiv preprint, arXiv: 1711.05189, 2017
N. Papernot, P. McDaniel, X. Wu, S. Jha and A. Swami, "Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks," 2016 IEEE Symposium on Security and Privacy (SP), 2016, pp. 582-597, doi: 10.1109/SP.2016.41.
T. Miyato, S. Aeda, M. Koyama, et al. Virtual adversarial training: a regularization method for supervised and semi-supervised learning[J]. IEEE transactions on pattern analysis and machine intelligence, 2018, 41(8): 1979 − 1993.
Zhang, J., & Jiang, Y. (2022). A Data Augmentation Method for Vertical Federated Learning. Wireless Communications and Mobile Computing, 2022.
V. Zantedeschi, M. I. Nicolae, A. Rawat. Efficient defenses against adversarial attacks[C]//Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security.Dallas,Texas, USA:ACM, 2017: 39 - 49.
J. Zhou,X. Dong,Z. Cao,Research Progress on Privacy Protection of Recommendation System[J]. Journal of Computer Research and Development, 2019, 56(10): 2033 − 2048.
J. Zhou,X. Dong,Z. Cao, et al. Research progress on big data security and privacy protection[J]. Journal of Computer Research and Development, 2016, 53(10): 2137 −2151.
S. Ji, J. Li, T. Du , et al. A Review of Interpretable Methods, Applications and Safety Research on Machine Learning Models[J]. Journal of Computer Research and Development, 2019, 56(10): 2071 – 2096
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
