Privacy and Security in Federated Learning: A Survey
Source abstract
Abstract
In recent years, privacy concerns have become a serious issue for companies wishing to protect economic models and comply with end-user expectations. In the same vein, some countries now impose, by law, constraints on data use and protection. Such context thus encourages machine learning to evolve from a centralized data and computation approach to decentralized approaches. Specifically, Federated Learning (FL) has been recently developed as a solution to improve privacy, relying on local data to train local models, which collaborate to update a global model that improves generalization behaviors. However, by definition, no computer system is entirely safe. Security issues, such as data poisoning and adversarial attack, can introduce bias in the model predictions. In addition, it has recently been shown that the reconstruction of private raw data is still possible. This paper presents a comprehensive study concerning various privacy and security issues related to federated learning. Then, we identify the state-of-the-art approaches that aim to counteract these problems. Findings from our study confirm that the current major security threats are poisoning, backdoor, and Generative Adversarial Network (GAN)-based attacks, while inference-based attacks are the most critical to the privacy of FL. Finally, we identify ongoing research directions on the topic. This paper could be used as a reference to promote cybersecurity-related research on designing FL-based solutions for alleviating future challenges.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Privacy-Preserving Technologies in Data · Adversarial Robustness in Machine Learning · Ethics and Social Impacts of AI
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Polytech Annecy-Chambéry, Savoie Mont Blanc University, F-74944 Annecy, France
LISTIC, Savoie Mont Blanc University, F-74944 Annecy, France
References (63)
Show source-provided references
1. Al Hayajneh, A., Bhuiyan, M.Z.A., and McAndrew, I. (2020). Improving internet of things (IoT) security with software-defined networking (SDN). Computers, 9.10.3390/computers9010008 ↗
2. The evolution of the Internet of Things (IoT) over the past 20 years10.1016/j.cie.2021.107174 ↗
3. McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B.A. (2017, January 20–22). Communication-efficient learning of deep networks from decentralized data. Proceedings of the Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA.
4. Biscotti: A blockchain system for private and secure federated learning10.1109/TPDS.2020.3044223 ↗
5. Biggio, B., Nelson, B., and Laskov, P. (2012). Poisoning Attacks against Support Vector Machines. arXiv.
6. Zhang, J., Chen, J., Wu, D., Chen, B., and Yu, S. (2019, January 5–8). Poisoning attack in federated learning using generative adversarial nets. Proceedings of the 2019 18th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/13th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE), Rotorua, New Zealand.10.1109/TrustCom/BigDataSE.2019.00057 ↗
7. Deep leakage from gradients
8. Li, Q., Wen, Z., and He, B. (2019). Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection. arXiv.
9. Federated learning
10. Advances and open problems in federated learning10.1561/2200000083 ↗
11. Tang, Z., Shi, S., Chu, X., Wang, W., and Li, B. (2020). Communication-Efficient Distributed Deep Learning: A Comprehensive Survey. arXiv.
12. Privacy and security in the big data paradigm
13. McMahan, B., and Ramag, D. (2022, September 26). Federated Learning: Collaborative Machine Learning without Centralized Training Data. Available online: https://ai.googleblog.com/2017/04/federated-learning-collaborative.html.
14. Federated learning for predicting clinical outcomes in patients with COVID-1910.1038/s41591-021-01506-3 ↗
15. Hu, C., Jiang, J., and Wang, Z. (2019). Decentralized Federated Learning: A Segmented Gossip Approach. arXiv.
16. Vanhaesebrouck, P., Bellet, A., and Tommasi, M. (2017, January 20–22). Decentralized collaborative learning of personalized models over networks. Proceedings of the Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA.
17. Reddi, S.J., Charles, Z., Zaheer, M., Garrett, Z., Rush, K., Konečnỳ, J., Kumar, S., and McMahan, H.B. Adaptive Federated Optimization. Proceedings of the International Conference on Learning Representations (ICLR), Virtual Conference.
18. Federated optimization in heterogeneous networks
19. Wang, H., Yurochkin, M., Sun, Y., Papailiopoulos, D., and Khazaeni, Y. Federated learning with matched averaging. Proceedings of the International Conference on Learning Representations (ICLR), Virtual Conference.
20. OWSAP (2022, September 26). OWSAP Defination for Vulnerability. Available online: https://owasp.org/www-community/vulnerabilities/.
21. Bhagoji, A.N., Chakraborty, S., Mittal, P., and Calo, S. (2019, January 9–15). Analyzing federated learning through an adversarial lens. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA.
22. Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., and Shmatikov, V. (2020, January 26–28). How to backdoor federated learning. Proceedings of the International Conference on Artificial Intelligence and Statistics, Palermo, Sicily, Italy.
23. The law of cyber-attack
24. A survey on security and privacy of federated learning10.1016/j.future.2020.10.007 ↗
25. Lyu, L., Yu, H., and Yang, Q. (2020). Threats to federated learning: A survey. arXiv.10.1007/978-3-030-63076-8_1 ↗
26. Tolpegin, V., Truex, S., Gursoy, M.E., and Liu, L. (2020, January 14–18). Data poisoning attacks against federated learning systems. Proceedings of the European Symposium on Research in Computer Security, Guildford, UK.10.1007/978-3-030-58951-6_24 ↗
27. Poisongan: Generative poisoning attacks against federated learning in edge computing systems10.1109/JIOT.2020.3023126 ↗
28. Rodríguez-Barroso, N., Martínez-Cámara, E., Luzón, M., González Seco, G., Ángel Veganzones, M., and Herrera, F. (2020). Dynamic Federated Learning Model for Identifying Adversarial Clients. arXiv.
29. Cao, D., Chang, S., Lin, Z., Liu, G., and Sun, D. (2019, January 4–6). Understanding distributed poisoning attack in federated learning. Proceedings of the 2019 IEEE 25th International Conference on Parallel and Distributed Systems (ICPADS), Tianjin, China.10.1109/ICPADS47876.2019.00042 ↗
30. Contamination attacks and mitigation in multi-party machine learning
31. Li, D., and Wang, J. (2019). FedMD: Heterogenous Federated Learning via Model Distillation. arXiv.
32. Liu, K., Dolan-Gavitt, B., and Garg, S. (2018). Fine-pruning: Defending against backdooring attacks on deep neural networks. Proceedings of the International Symposium on Research in Attacks, Intrusions, and Defenses, Crete, Greece, 10–12 September 2018, Springer.10.1007/978-3-030-00470-5_13 ↗
33. Nakamoto, S. (2008). Bitcoin: A peer-to-peer electronic cash system. Decentralized Bus. Rev., 21260.
34. Blockchain technology: Beyond bitcoin
35. Majeed, U., and Hong, C.S. (2019, January 18–20). FLchain: Federated learning via MEC-enabled blockchain network. Proceedings of the 2019 20th Asia-Pacific Network Operations and Management Symposium (APNOMS), Matsue, Japan.10.23919/APNOMS.2019.8892848 ↗
36. Blockchained on-device federated learning10.1109/LCOMM.2019.2921755 ↗
37. Kalapaaking, A.P., Khalil, I., Rahman, M.S., Atiquzzaman, M., Yi, X., and Almashor, M. (2022). Blockchain-based Federated Learning with Secure Aggregation in Trusted Execution Environment for Internet-of-Things. IEEE Trans. Ind. Inform.10.1109/TII.2022.3170348 ↗
38. Privacy preservation in federated learning: An insightful survey from the GDPR perspective10.1016/j.cose.2021.102402 ↗
39. Nasr, M., Shokri, R., and Houmansadr, A. (2019, January 19–23). Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning. Proceedings of the 2019 IEEE Symposium on Security and Privacy (SP), San Francisco, CA, USA.10.1109/SP.2019.00065 ↗
40. Melis, L., Song, C., De Cristofaro, E., and Shmatikov, V. (2019, January 19–23). Exploiting unintended feature leakage in collaborative learning. Proceedings of the 2019 IEEE Symposium on Security and Privacy (SP), San Francisco, CA, USA.10.1109/SP.2019.00029 ↗
41. Inverting gradients-how easy is it to break privacy in federated learning?
42. Xu, C., and Neglia, G. (, 2021). What else is leaked when eavesdropping Federated Learning?. Proceedings of the CCS workshop Privacy Preserving Machine Learning, Virtual Event, USA.
43. Analyzing user-level privacy attack against federated learning10.1109/JSAC.2020.3000372 ↗
44. Wang, Z., Song, M., Zhang, Z., Song, Y., Wang, Q., and Qi, H. (May, January 29). Beyond inferring class representatives: User-level privacy leakage from federated learning. Proceedings of the IEEE INFOCOM 2019-IEEE Conference on Computer Communications, Paris, France.10.1109/INFOCOM.2019.8737416 ↗
45. Truong, N., Sun, K., Wang, S., Guitton, F., and Guo, Y. (2020). Privacy preservation in federated learning: Insights from the gdpr perspective. arXiv.10.1016/j.cose.2021.102402 ↗
46. Hitaj, B., Ateniese, G., and Perez-Cruz, F. (November, January 30). Deep models under the GAN: Information leakage from collaborative deep learning. Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, Dallas, TX, USA.10.1145/3133956.3134012 ↗
47. Privacy-preserving deep learning via additively homomorphic encryption
48. Zhao, B., Reddy Mopuri, K., and Bilen, H. (2020). iDLG: Improved Deep Leakage from Gradients. arXiv.
49. Zari, O., Xu, C., and Neglia, G. (2021). Efficient passive membership inference attack in federated learning. arXiv.
50. Lin, Y., Han, S., Mao, H., Wang, Y., and Dally, W.J. (2017). Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training. arXiv.
51. Communication-efficient hierarchical federated learning for IoT heterogeneous systems with imbalanced data10.1016/j.future.2021.10.016 ↗
52. Augenstein, S., McMahan, H.B., Ramage, D., Ramaswamy, S., Kairouz, P., Chen, M., Mathews, R., and y Arcas, B.A. (2019, January 6–9). Generative Models for Effective ML on Private, Decentralized Datasets. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA.
53. Ghazi, B., Pagh, R., and Velingker, A. (2019). Scalable and Differentially Private Distributed Aggregation in the Shuffled Model. arXiv.
54. Verifynet: Secure and verifiable federated learning10.1109/TIFS.2019.2929409 ↗
55. Privacy-preserving blockchain-based federated learning for IoT devices10.1109/JIOT.2020.3017377 ↗
56. Efficient and privacy-enhanced federated learning for industrial artificial intelligence10.1109/TII.2019.2945367 ↗
57. A survey on bias and fairness in machine learning10.1145/3457607 ↗
58. Ferraguig, L., Djebrouni, Y., Bouchenak, S., and Marangozova, V. (, January July). Survey of Bias Mitigation in Federated Learning. Proceedings of the Conférence Francophone D’informatique en Parallélisme, Architecture et Système, Lyon, France.
59. Briggs, C., Fan, Z., and Andras, P. (2020, January 19–24). Federated learning with hierarchical clustering of local updates to improve training on non-IID data. Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK.10.1109/IJCNN48605.2020.9207469 ↗
60. Federated Reconstruction: Partially Local Federated Learning
61. Swarm learning for decentralized artificial intelligence in cancer histopathology10.1038/s41591-022-01768-5 ↗
62. Swarm learning for decentralized healthcare10.1007/s00105-021-04940-z ↗
63. Swarm learning for decentralized and confidential clinical machine learning10.1038/s41586-021-03583-3 ↗