VerifyNet: Secure and Verifiable Federated Learning

By Guowen Xu, Hongwei Li, Sen Liu, Kan Yang, Xiaodong Lin. 2020

743 citations recorded by the source corpus.

As an emerging training model with neural networks, federated learning has received widespread attention due to its ability to update parameters without collecting users’ raw data. However, since adversaries can track and derive participants’ privacy from the shared gradients, federated learning is still exposed to various security and privacy threats. In this paper, we consider two major issues in the training process over deep neural networks (DNNs): 1) how to protect user’s privacy (i.e., local gradients) in the training process and 2) how to verify the integrity (or correctness) of the aggregated results returned from the server. To solve the above problems, several approaches focusing on secure or privacy-preserving federated learning have been proposed and applied in diverse scenarios. However, it is still an open problem enabling clients to verify whether the cloud server is operating correctly, while guaranteeing user’s privacy in the training process. In this paper, we propose VerifyNet, the first privacy-preserving and verifiable federated learning framework. In specific, we first propose a double-masking protocol to guarantee the confidentiality of users’ local gradients during the federated learning. Then, the cloud server is required to provide the Proof about the correctness of its aggregated results to each user. We claim that it is impossible that an adversary can deceive users by forging Proof, unless it can solve the NP-hard problem adopted in our model. In addition, VerifyNet is also supportive of users dropping out during the training process. The extensive experiments conducted on real-world data also demonstrate the practical performance of our proposed scheme.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

On Safeguarding Privacy and Security in the Framework of Federated Learning (2019, background): “Researchers have considered the situation when one of the members of a FL system maliciously attacks others by allowing a backdoor to be inserted to filch others’ data [14].”
Industrial Artificial Intelligence in Industry 4.0 - Systematic Review, Challenges and Outlook (2020, background): “…of addressing critical issues of data privacy and security, recent studies have shown that even in federated learning scenarios several risks can be found, particularly regarding reverse-engineering attacks that can extract sensitive information about the datasets directly from the model [96].”
Efficient and Privacy-Enhanced Federated Learning for Industrial Artificial Intelligence (2020, background): “However, recent studies have shown that it also brings various privacy concerns [14], [15].”
Enhancing Privacy via Hierarchical Federated Learning (2020, background): “Second, the time required for verification grows typically exponentially with the number of users [4], [31], which renders these approaches unscalable, and thus unsuitable for large-scale applications.”
Federated Learning in Smart City Sensing: Challenges and Opportunities (2020, neutral): “Mobile phones and wearable devices are very common data generation devices in modern times [119], which generate huge amounts of data in various forms every day.”
Blockchain-Federated-Learning and Deep Learning Models for COVID-19 Detection Using CT Imaging (2020, background): “The availability of such conﬁdential data is not possible due to the absence of privacy-preserving approach for the health care centers [13], [14], [15], [16], [17], [18], [19], [20], [21], [22].”
FedLoc: Federated Learning Framework for Data-Driven Cooperative Localization and Location Data Processing (2020, background): “Other than the above schemes, to verify the correctness of the final aggregation result, a privacy-preserving and verifiable federated learning protocol has been designed with a homomorphic hash function and a secret sharing protocol [79].”
A Robust Privacy-Preserving Federated Learning Model Against Model Poisoning Attacks (2024, background): “In line with the approach in [2], we consider the auditor a Trusted Authority, ensuring trustworthiness and independence from other entities.”
Self-Balancing Federated Learning With Global Imbalanced Data in Mobile Systems (2021, background): “Recent research on federated learning has focused on reducing communication overhead [9], [10], [26], [27] and protecting privacy [28], [29], [30], [31], but only a few studies have noticed the problem of accuracy degradation due to imbalance [15], [32], [33].”
A Survey on federated learning* (2020, background): “Thereafter Xu et al. devised VerifyNet which can verify correctness of returned model from cloud [46].”
Privacy-Enhanced Federated Learning Against Poisoning Adversaries (2021, background): “Unlike traditional deep learning that centralizes all training data, FL is a promising distributed setting that allows all data owners to keep data local [27].”
Privacy-Preserving Traffic Flow Prediction: A Federated Learning Approach (2020, background): “[34] proposed VerifyNet, which is the first framework to protect the privacy and verifiable FL.”
Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues (2020, background): “[25] introduce VerifyNet, a FL framework that enhances the privacy of local gradients with a double-masking protocol.”
Privacy‐preserving federated learning based on multi‐key homomorphic encryption (2021, neutral): “Xu et al. [34] proposed privacy preserving and veriﬁable collaborative learning, which uses double masking to ensure the conﬁdentiality of the individual gradients.”
A review of applications in federated learning (2020, background): “Thereafter Xu et al., (2020) devised VerifyNet, the first protocol that can verify correctness of returned model from cloud.”
Secure SVM Training Over Vertically-Partitioned Datasets Using Consortium Blockchain for Vehicular Social Networks (2020, background): “Machine learning (ML) and deep learning have drawn the attention of reseachers from many domains [7]–[11].”
Data Poisoning Attacks on Federated Machine Learning (2020, background): “However, none of the current works study poisoning attacks on federated machine learning [11], [17], [18], where the training data are distributed across multiple devices (e.”
A Comprehensive Survey of Privacy-preserving Federated Learning (2021, methodology): “In Reference [198], secure sharing and additive perturbation are deployed in a FL method to protect the local gradients in the training process.”