nach oben

Erschienen in:

2020 | OriginalPaper | Buchkapitel

Threats to Federated Learning

verfasst von : Lingjuan Lyu, Han Yu, Jun Zhao, Qiang Yang

Erschienen in: Federated Learning

Verlag: Springer International Publishing

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized approach of training artificial intelligence (AI) models is facing strong challenges. Federated learning (FL) has recently emerged as a promising solution under this new reality. Existing FL protocol design has been shown to exhibit vulnerabilities which can be exploited by adversaries both within and outside of the system to compromise data privacy. It is thus of paramount importance to make FL system designers aware of the implications of future FL algorithm design on privacy-preservation. Currently, there is no survey on this topic. In this chapter, we bridge this important gap in FL literature. By providing a concise introduction to the concept of FL, and a unique taxonomy covering threat models and two major attacks on FL: 1) poisoning attacks and 2) inference attacks, we provide an accessible review of this important topic. We highlight the intuitions, key techniques as well as fundamental assumptions adopted by various attacks, and discuss promising future research directions towards more robust privacy preservation in FL.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Nächstes Kapitel Deep Leakage from Gradients

https://www.ntu.edu.sg/home/han.yu/FL.html.

Abadi, M., et al.: Deep learning with differential privacy. In: CCS, pp. 308–318 (2016)

Agarwal, N., Suresh, A.T., Yu, F.X.X., Kumar, S., McMahan, B.: cpSGD: communication-efficient and differentially-private distributed SGD. In: NeurIPS, pp. 7564–7575 (2018)

Aono, Y., Hayashi, T., Wang, L., Moriai, S., et al.: Privacy-preserving deep learning via additively homomorphic encryption. IEEE Trans. Inf. Forensics Secur. 13(5), 1333–1345 (2018)CrossRef

Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., Shmatikov, V.: How to backdoor federated learning. CoRR, arXiv:1807.00459 (2018)

Barreno, M., Nelson, B., Sears, R., Joseph, A.D., Tygar, J.D.: Can machine learning be secure? In: ICCS, pp. 16–25 (2006)

Bernstein, J., Zhao, J., Azizzadenesheli, K., Anandkumar, A.: signSGD with majority vote is communication efficient and fault tolerant. CoRR, arXiv:1810.05291 (2018)

Bhagoji, A.N., Chakraborty, S., Mittal, P., Calo, S.: Analyzing federated learning through an adversarial lens. CoRR, arXiv:1811.12470 (2018)

Bhowmick, A., Duchi, J., Freudiger, J., Kapoor, G., Rogers, R.: Protection against reconstruction and its applications in private federated learning. CoRR, arXiv:1812.00984 (2018)

Biggio, B., Nelson, B., Laskov, P.: Support vector machines under adversarial label noise. In: ACML, pp. 97–112 (2011)

10.

Biggio, B., Nelson, B., Laskov, P.: Poisoning attacks against support vector machines. CoRR, arXiv:1206.6389 (2012)

11.

Blanchard, P., Guerraoui, R., Stainer, J., et al.: Machine learning with adversaries: Byzantine tolerant gradient descent. In: NeurIPS, pp. 119–129 (2017)

12.

Bonawitz, K., et al.: Practical secure aggregation for privacy-preserving machine learning. In: CCS, pp. 1175–1191 (2017)

13.

Chang, H., Shejwalkar, V., Shokri, R., Houmansadr, A.: Cronus: robust and heterogeneous collaborative learning with black-box knowledge transfer. CoRR, arXiv:1912.11279 (2019)

14.

Chen, L., Wang, H., Charles, Z., Papailiopoulos, D.: Draco: Byzantine-resilient distributed training via redundant gradients. CoRR, arXiv:1803.09877 (2018)

15.

Chen, Y., Su, L., Xu, J.: Distributed statistical machine learning in adversarial settings: Byzantine gradient descent. Proc. ACM Meas. Anal. Comput. Syst. 1(2), 44 (2017)

16.

Fredrikson, M., Jha, S., Ristenpart, T.: Model inversion attacks that exploit confidence information and basic countermeasures. In: CCS, pp. 1322–1333 (2015)

17.

Fung, C., Yoon, C.J., Beschastnikh, I.: Mitigating sybils in federated learning poisoning. CoRR, arXiv:1808.04866 (2018)

18.

Gao, D., Liu, Y., Huang, A., Ju, C., Yu, H., Yang, Q.: Privacy-preserving heterogeneous federated transfer learning. In: IEEE BigData (2019)

19.

Gu, T., Dolan-Gavitt, B., Garg, S.: BadNets: identifying vulnerabilities in the machine learning model supply chain. CoRR, arXiv:1708.06733 (2017)

20.

Hardy, S., et al.: Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption. CoRR, arXiv:1711.10677 (2017)

21.

Hitaj, B., Ateniese, G., Pérez-Cruz, F.: Deep models under the GAN: information leakage from collaborative deep learning. In: CSS, pp. 603–618 (2017)

22.

Huang, L., Joseph, A.D., Nelson, B., Rubinstein, B.I., Tygar, J.D.: Adversarial machine learning. In: Proceedings of the 4th ACM Workshop on Security and Artificial Intelligence, pp. 43–58 (2011)

23.

Kairouz, P., et al.: Advances and open problems in federated learning. CoRR, arXiv:1912.04977 (2019)

24.

Kantarcioglu, M., Clifton, C.: Privacy-preserving distributed mining of association rules on horizontally partitioned data. IEEE Trans. Knowl. Data Eng. 16(9), 1026–1037 (2004)CrossRef

25.

Li, D., Wang, J.: FedMD: heterogenous federated learning via model distillation. arXiv preprint arXiv:1910.03581 (2019)

26.

Li, H., Ota, K., Dong, M.: Learning IoT in edge: deep learning for the Internet of Things with edge computing. IEEE Netw. 32(1), 96–101 (2018)CrossRef

27.

Li, T., Sahu, A.K., Talwalkar, A., Smith, V.: Federated learning: challenges, methods, and future directions. CoRR, arXiv:1908.07873 (2019)

28.

Lingjuan Lyu, X.X., Wang, Q.: Collaborative fairness in federated learning. arxiv.org/abs/2008.12161v1 (2020)

29.

Liu, Y., et al.: Fedvision: an online visual object detection platform powered by federated learning. In: IAAI (2020)

30.

Lyu, L., Bezdek, J.C., He, X., Jin, J.: Fog-embedded deep learning for the Internet of Things. IEEE Trans. Ind. Inform. 15(7), 4206–4215 (2019)CrossRef

31.

Lyu, L., Bezdek, J.C., Jin, J., Yang, Y.: FORESEEN: towards differentially private deep inference for intelligent Internet of Things. IEEE J. Sel. Areas Commun. 38, 2418–2429 (2020)CrossRef

32.

Lyu, L., Li, Y., Nandakumar, K., Yu, J., Ma, X.: How to democratise and protect AI: fair and differentially private decentralised deep learning. IEEE Trans. Dependable Secur. Comput

33.

Lyu, L., et al.: Towards fair and privacy-preserving federated deep models. IEEE Trans. Parallel Distrib. Syst. 31(11), 2524–2541 (2020)CrossRef

34.

McMahan, B., Moore, E., Ramage, D., Hampson, S., y Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics, pp. 1273–1282 (2017)

35.

McMahan, H.B., Moore, E., Ramage, D., y Arcas, B.A.: Federated learning of deep networks using model averaging. CoRR, arXiv:1602.05629 (2016)

36.

McMahan, H.B., Ramage, D., Talwar, K., Zhang, L.: Learning differentially private recurrent language models. In: ICLR (2018)

37.

Melis, L., Song, C., De Cristofaro, E., Shmatikov, V.: Exploiting unintended feature leakage in collaborative learning. In: SP, pp. 691–706 (2019)

38.

Nasr, M., Shokri, R., Houmansadr, A.: Comprehensive privacy analysis of deep learning: passive and active white-box inference attacks against centralized and federated learning. In: SP, pp. 739–753 (2019)

39.

Pan, X., Zhang, M., Ji, S., Yang, M.: Privacy risks of general-purpose language models. In: 2020 IEEE Symposium on Security and Privacy (SP), pp. 1314–1331. IEEE (2020)

40.

Pan, X., Zhang, M., Wu, D., Xiao, Q., Ji, S., Yang, M.: Justinian’s GAAvernor: robust distributed learning with gradient aggregation agent. In: USENIX Security Symposium (2020)

41.

Phong, L.T., Aono, Y., Hayashi, T., Wang, L., Moriai, S.: Privacy-preserving deep learning via additively homomorphic encryption. IEEE Trans. Inf. Forensics Secur. 13(5), 1333–1345 (2018)CrossRef

42.

Shafahi, A., et al.: Poison frogs! Targeted clean-label poisoning attacks on neural networks. In: NeurIPS, pp. 6103–6113 (2018)

43.

Shokri, R., Stronati, M., Song, C., Shmatikov, V.: Membership inference attacks against machine learning models. In: SP, pp. 3–18 (2017)

44.

Su, L., Xu, J.: Securing distributed machine learning in high dimensions. CoRR, arXiv:1804.10140 (2018)

45.

Szegedy, C., et al.: Intriguing properties of neural networks. CoRR, arXiv:1312.6199 (2013)

46.

Vaidya, J., Clifton, C.: Privacy preserving association rule mining in vertically partitioned data. In: KDD, pp. 639–644 (2002)

47.

Yang, Q., Liu, Y., Chen, T., Tong, Y.: Federated machine learning: concept and applications. ACM Trans. Intell. Syst. Technol. (TIST) 10(2), 1–19 (2019)CrossRef

48.

Yang, Q., Liu, Y., Cheng, Y., Kang, Y., Chen, T., Yu, H.: Federated Learning. Morgan & Claypool Publishers, San Rafael (2019)CrossRef

49.

Yin, D., Chen, Y., Ramchandran, K., Bartlett, P.: Byzantine-robust distributed learning: towards optimal statistical rates. CoRR, arXiv:1803.01498 (2018)

50.

Zhao, B., Mopuri, K.R., Bilen, H.: iDLG: improved deep leakage from gradients. CoRR, arXiv:2001.02610 (2020)

51.

Zhao, Y., et al.: Local differential privacy based federated learning for Internet of Things. arXiv preprint arXiv:2004.08856 (2020)

52.

Zhu, L., Liu, Z., Han, S.: Deep leakage from gradients. In: NeurIPS, pp. 14747–14756 (2019)

Titel: Threats to Federated Learning
verfasst von: Lingjuan Lyu
Han Yu
Jun Zhao
Qiang Yang
Verlag: Springer International Publishing
Buch: Federated Learning
Print ISBN: 978-3-030-63075-1

Electronic ISBN: 978-3-030-63076-8

Copyright-Jahr: 2020
DOI: https://doi.org/10.1007/978-3-030-63076-8_1

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Premium Partner