Abstract
Web 3.0 emphasizes the decentralization of data assets to build a more open, trustworthy, and user-empowered data ecosystem. Therefore, users have complete sovereignty and ownership over their data in Web 3.0. However, the high degree of personal control over data limits the mobility and interoperability of data, forming data silos that restrict the development of Web 3.0. As an advanced paradigm that breaks down data silos, federated learning can promote collaborative sharing of data assets while protecting user privacy. However, in the open and complex environment of Web 3.0, federated learning is vulnerable to attacks. In the Web 3.0 environment, inquisitive servers and clients might exploit global models to conduct passive inference assaults, aiming to illicitly acquire data assets from training data. Additionally, the global model also faces the threat of malicious clients launching active inference attacks and submitting false local gradients. We introduce PILE, a resilient framework for federated learning that safeguards the confidentiality of both local gradients and global models. Furthermore, it guarantees their integrity through the verification of gradients. In PILE, we propose a scheme for gradient validation using local gradients. It includes two components of zero-knowledge proof so that the local gradient and global model do not need to be publicly disclosed. In addition, we have demonstrated the security of PILE and conducted experimental evaluations of the scheme under both active and passive inference attacks. The experiment results show that PILE can provide strong privacy protection and model training robustness for data assets in Web 3.0.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi M, Chu A, Goodfellow I, McMahan HB, Mironov I, Talwar K, Zhang L (2016) Deep learning with differential privacy. In: Proceedings of the 2016 ACM SIGSAC conference on computer and communications security, pp 308–318
Blanchard P, El Mhamdi EM, Guerraoui R, Stainer J (2017) Machine learning with adversaries: Byzantine tolerant gradient descent. In: Advances in neural information processing systems, 30.
Boyle E, Gilboa N, Ishai Y (2016) Function secret sharing: improvements and extensions. In: Proceedings of the 2016 ACM SIGSAC conference on computer and communications security, pp. 1292–1303
Cao X, Fang M, Liu J, Gong NZ (2020)0 FLTrust: Byzantine-robust federated learning via trust bootstrapping. arXiv preprint arXiv:2012.13995
Cheng Y, Liu Y, Chen T, Yang Q (2020) Federated learning for privacy-preserving AI. Commun ACM 63(12):33–36
Cramer R, Damgård I, Nielsen JB (2001) Multiparty computation from threshold homomorphic encryption. In: Advances in cryptology–EUROCRYPT 2001: international conference on the theory and application of cryptographic techniques Innsbruck, Austria, May 6–10, 2001 proceedings 20. Springer, pp 280–300
Damgård I, Jurik M (2001) A generalisation, a simplification and some applications of Paillier’s probabilistic public-key system. In: Public key cryptography: 4th international workshop on practice and theory in public key cryptosystems, PKC 2001 Cheju Island, February 13–15, 2001 proceedings 4. Springer, pp 119–136
Dwork C (2006) Differential privacy. In: International colloquium on automata, languages, and programming. Springer, Berlin, pp 1–12
Fang M, Cao X, Jia J, Gong N (2020) Local model poisoning attacks to {Byzantine-Robust} federated learning. In: 29th USENIX security symposium (USENIX security 20), pp 1605–1622
Geyer RC, Klein T, Nabi M (2017) Differentially private federated learning: a client level perspective. arXiv preprint arXiv:1712.07557
Ghodsi Z, Gu T, Garg S (2017) SafetyNets: verifiable execution of deep neural networks on an untrusted cloud. In: Advances in neural information processing systems, 30
Goldreich O (2009) Foundations of cryptography: volume 2, basic applications. Cambridge University Press, Cambridge
Hannila H, Silvola R, Harkonen J, Haapasalo H (2022) Data-driven begins with data; potential of data assets. J Comput Inf Syst 62(1):29–38
Huang L, Wu C, Wang B, Ouyang Q (2018) Big-data-driven safety decision-making: a conceptual framework and its influencing factors. Safety Sci 109:46–56
Jagielski M, Oprea A, Biggio B, Liu C, Nita-Rotaru C, Li B (2018) Manipulating machine learning: poisoning attacks and countermeasures for regression learning. In: 2018 IEEE symposium on security and privacy (SP). IEEE, pp 19–35
Kairouz P, McMahan HB, Avent B, Bellet A, Bennis M, Bhagoji AN, Bonawitz K, Charles Z, Cormode G, Cummings R, et al (2021) Advances and open problems in federated learning. Foundat Trends® Mach Learn 14(1–2):1–210
Katz J, Lindell Y (2007) Introduction to modern cryptography: principles and protocols. Chapman and Hall/CRC, Boca Raton
Keller M, Pastro V, Rotaru D (2018) Overdrive: making SPDZ great again. In: Annual international conference on the theory and applications of cryptographic techniques. Springer, pp 158–189
Koh PW, Steinhardt J, Liang P (2022) Stronger data poisoning attacks break data sanitization defenses. Mach Learn, 111(1):1–47
McMahan B, Moore E, Ramage D, Hampson S, Arcas BAy (2017) Communication-efficient learning of deep networks from decentralized data. In: Artificial intelligence and statistics. PMLR, pp 1273–1282
Mohassel P, Zhang Y (2017) SecureML: a system for scalable privacy-preserving machine learning. In: 2017 IEEE symposium on security and privacy (SP). IEEE, pp 19–38
Nasr M, Shokri R, Houmansadr A (2019) Comprehensive privacy analysis of deep learning: passive and active white-box inference attacks against centralized and federated learning. In: 2019 IEEE symposium on security and privacy (SP). IEEE, pp 739–753
Nasr M, Shokri R, Houmansadr A (2018) Machine learning with membership privacy using adversarial regularization. In: Proceedings of the 2018 ACM SIGSAC conference on computer and communications security, pp 634–646
Nishide T, Sakurai K (2011) Distributed paillier cryptosystem without trusted dealer. In: Information security applications: 11th international workshop, WISA 2010, Jeju Island, August 24–26, 2010, revised selected papers 11. Springer, pp 44–60
Paillier P (1999) Public-key cryptosystems based on composite residuosity classes. In: Advances in cryptology—EUROCRYPT, pp 223–239
Rathor S, Zhang M, Im T (2023) Web 3.0 and sustainability: challenges and research opportunities. Sustainability 15(20):15126
Sathya SS, Vepakomma P, Raskar R, Ramachandra R, Bhattacharya S (2018) A review of homomorphic encryption libraries for secure computation. arXiv preprint arXiv:1812.02428
Song L, Mittal P (2021) Systematic evaluation of privacy risks of machine learning models. In: 30th USENIX security symposium (USENIX security 21), pp 2615–2632
Veugen T, Attema T, Spini G (2019). An implementation of the Paillier crypto system with threshold decryption without a trusted dealer. Cryptology ePrint archive
Xu G, Li H, Liu S, Yang K, Lin X (2019) VerifyNet: secure and verifiable federated learning. IEEE Trans Inf Forens Secur 15:911–926
Yang X, Feng Y, Fang W, Shao J, Tang X, Xia S-T, Lu R (2022) An accuracy-lossless perturbation method for defending privacy attacks in federated learning. In: Proceedings of the ACM web conference, pp 732–742
Yuan D, Li Q, Li G, Wang Q, Ren K (2019) PriRadar: a privacy-preserving framework for spatial crowdsourcing. IEEE Trans Inf Forens Secur 15:299–314
Zhao J, Zhu H, Wang F, Lu R, Liu Z, Li H (2022) PVD-FL: a privacy-preserving and verifiable decentralized federated learning framework. IEEE Trans Inf Forens Secur 17:2059–2073
Zheng W, Popa RA, Gonzalez JE, Stoica I (2019). Helen: maliciously secure coopetitive learning for linear models. In: 2019 IEEE symposium on security and privacy (SP). IEEE, pp 724–738
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Shen, M., Tang, X., Wang, W., Zhu, L. (2024). Verifiable Privacy-Preserving Federated Learning in Web 3.0. In: Security and Privacy in Web 3.0. Digital Privacy and Security. Springer, Singapore. https://doi.org/10.1007/978-981-97-5752-7_3
Download citation
DOI: https://doi.org/10.1007/978-981-97-5752-7_3
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-5751-0
Online ISBN: 978-981-97-5752-7
eBook Packages: Computer ScienceComputer Science (R0)