A Privacy-Preserving and Verifiable Federated Learning Scheme

Zhang, Xianglong; Fu, Anmin; Wang, Huaqun; Zhou, Chunyi; Chen, Zhenzhu

doi:10.1109/icc40277.2020.9148628

Cited by 62 publications

(38 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Homomorphic encryption allows a calculation directly to be conducted on a ciphertext to generate an encrypted result such that the decrypted result is the same as the result calculated on the corresponding plaintext. This scheme is an effective way to protect data privacy when exchanging intermediate parameters during the FL training process, and has been widely used in many FL methods [7,26,39,69,71,137,215,221,224]. For example, Phong et al [137] proposed using homomorphic encryption to protect gradient updates during the FL training process.…”

Section: Encryption-based Ppflmentioning

confidence: 99%

“…Learning. Because cryptographic technique-based FL methods tend to suffer from computation and communication overhead, and perturbation-based FL methods tend to degrade the data utility, in recent years, hybrid PPFL methods have been proposed to balance the tradeoff between data privacy and data utility [30,59,69,70,127,173,198,199,221,224]. For example, the hybrid PPFL methods in References [59,198,224] are based on homomorphic encryption and secret sharing.…”

Section: Hybrid Privacy-preserving Federatedmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Survey of Privacy-preserving Federated Learning

2021

View full text Add to dashboard Cite

The past four years have witnessed the rapid development of federated learning (FL). However, new privacy concerns have also emerged during the aggregation of the distributed intermediate results. The emerging privacy-preserving FL (PPFL) has been heralded as a solution to generic privacy-preserving machine learning. However, the challenge of protecting data privacy while maintaining the data utility through machine learning still remains. In this article, we present a comprehensive and systematic survey on the PPFL based on our proposed 5W-scenario-based taxonomy. We analyze the privacy leakage risks in the FL from five aspects, summarize existing methods, and identify future research directions.

show abstract

Section: Encryption-based Ppflmentioning

confidence: 99%

Section: Hybrid Privacy-preserving Federatedmentioning

confidence: 99%

A Comprehensive Survey of Privacy-preserving Federated Learning

2021

View full text Add to dashboard Cite

show abstract

“…Network training, however, has to be conducted offline and does not involve the untrusted party. Improved schemes have been proposed in [38], [7] using addictive homomorphic encryption to protect model updates, by Zhang et al [8] exploiting privacy-preserving and verifiable federated learning using the Paillier cryptosystem [10], as well as by Froelicher et al [39] who proposed a decentralized system for privacy-conscious statistical analysis on distributed datasets by applying the ElGamal Elliptic Curve additive homomorphic cryptosystem [40]. In these approaches, all participating devices share the same encryption and decryption key, so that private information may leak among devices.…”

Section: Privacy-preserving Federated Learningmentioning

confidence: 99%

“…Any participating device able to observe and analyze these updates may thus pose a threat to the privacy protection interests of other devices, which ultimately discourages participation in the training of a distributed model. homomorphic encryption (HE) enables the computation on encrypted model updates [7,8], all participants in these works share the same public key for encryption and, more importantly, the same secret key for decryption (Fig 1b).…”

Section: Introductionmentioning

confidence: 99%

Privacy-preserving Federated Learning based on Multi-key Homomorphic Encryption

Ma¹,

Naas²,

Sigg³

et al. 2021

Preprint

View full text Add to dashboard Cite

With the advance of machine learning and the internet of things (IoT), security and privacy have become key concerns in mobile services and networks. Transferring data to a central unit violates privacy as well as protection of sensitive data while increasing bandwidth demands. Federated learning mitigates this need to transfer local data by sharing model updates only. However, data leakage still remains an issue. In this paper, we propose xMK-CKKS, a multi-key homomorphic encryption protocol to design a novel privacy-preserving federated learning scheme. In this scheme, model updates are encrypted via an aggregated public key before sharing with a server for aggregation. For decryption, collaboration between all participating devices is required. This scheme prevents privacy leakage from publicly shared information in federated learning, and is robust to collusion between k < N − 1 participating devices and the server. Our experimental evaluation demonstrates that the scheme preserves model accuracy against traditional federated learning as well as secure federated learning with homomorphic encryption (MK-CKKS, Paillier) and reduces computational cost compared to Paillier based federated learning. The average energy consumption is 2.4 Watts, so that it is suited to IoT scenarios.

show abstract

“…Gao et al [39] proposed an end-to-end privacy protection scheme using HE for federated transfer learning, Zhou et al in [101] combined secret sharing and HE to protect privacy. While Zhang et al [102] introduced HE in Bayesian approaches to protect the privacy of vertical FL, references [103,104] added a coordinator, apart from clients and the central server, and let the coordinator take responsibility for specifying the security protocol including keys and processing functions. Stripelis et al [105] proposed a HE mechanism based on CKKS to reduce the difficulty of encryption and decryption.…”

mentioning

confidence: 99%

Applying Federated Learning in Software-Defined Networks: A Survey

Liao

Zhi

et al. 2022

Symmetry

View full text Add to dashboard Cite

Federated learning (FL) is a type of distributed machine learning approacs that trains global models through the collaboration of participants. It protects data privacy as participants only contribute local models instead of sharing private local data. However, the performance of FL highly relies on the number of participants and their contributions. When applying FL over conventional computer networks, attracting more participants, encouraging participants to contribute more local resources, and enabling efficient and effective collaboration among participants become very challenging. As software-defined networks (SDNs) enable open and flexible networking architecture with separate control and data planes, SDNs provide standardized protocols and specifications to enable fine-grained collaborations among devices. Applying FL approaches over SDNs can take use such advantages to address challenges. A SDN control plane can have multiple controllers organized in layers; the controllers in the lower layer can be placed in the network edge to deal with the asymmetries in the attached switches and hosts, and the controller in the upper layer can supervise the whole network centrally and globally. Applying FL in SDNs with a layered-distributed control plane may be able to protect the data privacy of each participant while improving collaboration among participants to produce higher-quality models over asymmetric networks. Accordingly, this paper aims to make a comprehensive survey on the related mechanisms and solutions that enable FL in SDNs. It highlights three major challenges, an incentive mechanism, privacy and security, and model aggregation, which affect the quality and quantity of participants, the security and privacy in model transferring, and the performance of the global model, respectively. The state of the art in mechanisms and solutions that can be applied to address such challenges in the current literature are categorized based on the challenges they face, followed by suggestions of future research directions. To the best of our knowledge, this work is the first effort in surveying the state of the art in combining FL with SDNs.

show abstract

A Privacy-Preserving and Verifiable Federated Learning Scheme

Cited by 62 publications

References 16 publications

A Comprehensive Survey of Privacy-preserving Federated Learning

A Comprehensive Survey of Privacy-preserving Federated Learning

Privacy-preserving Federated Learning based on Multi-key Homomorphic Encryption

Applying Federated Learning in Software-Defined Networks: A Survey

Contact Info

Product

Resources

About