Advancing Blockchain-based Federated Learning through Verifiable Off-chain Computations

Heiss, Jonathan; Grünewald, Elias; Haimerl, Nikolas; Schulte, Stefan; Tai, Stefan

doi:10.1109/blockchain55522.2022.00034

Cited by 23 publications

(7 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To increase the usability and have a trustless distributed aggregation process, multiple works such as [31], [33], [17], and [44] use smart contracts. Since functions in a smart contract run automatically and publicly, using them for aggregation removes the need for trusting a server and verifying the aggregation process.…”

Section: B Aggregation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Federify: A Verifiable Federated Learning Scheme Based on zkSNARKs and Blockchain

Keshavarzkalhori,

Pérez-Solà,

Navarro-Arribas

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Federated learning (FL) has emerged as an alternative to traditional machine learning in scenarios where training data is sensitive. In federated learning, training is held at end devices, and thus data does not need to leave users devices. However, most approaches to federated learning rely on a central server to coordinate the learning process which, in turn, introduces its own security and privacy problems. We propose Federify, a decentralized federated learning framework based on blockchain which employs homomorphic encryption and zero knowledge proofs to provide security, privacy, and transparency. The scheme preserves the confidentiality of both the data used for training and the local models using homomorphic encryption. zkSNARKs are used to provide security by verifying the contributions from the different agents, and transparency of both the learning process and the incentive mechanism is achieved by delegating coordination into a smart contract in a public blockchain. We have also implemented, deployed, and evaluated a proof of concept of our framework, to demonstrate its viability both in terms of computational resources needed and cost to train in a public generic blockchain such as Ethereum.

show abstract

Section: B Aggregation Methodsmentioning

confidence: 99%

“…Heiss et al In [17] present a design where all data owners' model computations are verified with zkSNARK. The clients compute a model locally and send their gradients to the smart contract for verification and aggregation.…”

Section: A Comparison Of Federify With the State Of The Artmentioning

confidence: 99%

Federify: A Verifiable Federated Learning Scheme Based on zkSNARKs and Blockchain

Keshavarzkalhori,

Pérez-Solà,

Navarro-Arribas

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Both references [89][90][91] used zero-knowledge proof methods to ensure that the submitted gradient values are from the real dataset, reference [90] used zero-knowledge proof techniques to construct a zk-Trainer to output gradient values as well as proofs simultaneously; reference [91] mentioned many computational details on this basis, including how to efficiently compute matrix operations in the gradient solution process, how to introduce auxiliary variables to simplify the computational process, and how to trade-off computational accuracy with computational complexity. Both solutions mention the problem that needs to be solved when applying zk-SNARK to BCFL.…”

Section: Figure 8: Zero-knowledge Proof Of Knowledge In Flmentioning

confidence: 99%

A Survey on Blockchain-Based Federated Learning: Categorization, Application and Analysis

Tang,

Zhang,

Niu

et al. 2024

CMES

View full text Add to dashboard Cite

Federated Learning (FL), as an emergent paradigm in privacy-preserving machine learning, has garnered significant interest from scholars and engineers across both academic and industrial spheres. Despite its innovative approach to model training across distributed networks, FL has its vulnerabilities; the centralized server-client architecture introduces risks of single-point failures. Moreover, the integrity of the global model-a cornerstone of FL-is susceptible to compromise through poisoning attacks by malicious actors. Such attacks and the potential for privacy leakage via inference starkly undermine FL's foundational privacy and security goals. For these reasons, some participants unwilling use their private data to train a model, which is a bottleneck in the development and industrialization of federated learning. Blockchain technology, characterized by its decentralized ledger system, offers a compelling solution to these issues. It inherently prevents single-point failures and, through its incentive mechanisms, motivates participants to contribute computing power. Thus, blockchain-based FL (BCFL) emerges as a natural progression to address FL's challenges. This study begins with concise introductions to federated learning and blockchain technologies, followed by a formal analysis of the specific problems that FL encounters. It discusses the challenges of combining the two technologies and presents an overview of the latest cryptographic solutions that prevent privacy leakage during communication and incentives in BCFL. In addition, this research examines the use of BCFL in various fields, such as the Internet of Things and the Internet of Vehicles. Finally, it assesses the effectiveness of these solutions.

show abstract

“…As proposed in [22,23], the schemes integrate the ZKPs and blockchain to construct the verifiable DFL framework, where the verification for updates is viewed as part of the consensus process, and miners are responsible for the verification before recording the updates into the blocks. In [24], ZKP-based verification is executed by smart contracts. However, these schemes use the blockchain as the black box or the third-party platform.…”

Section: Global Model Aggregatormentioning

confidence: 99%

“…, c s ) from multiple epochs can also be aggregated into the final ZKP proof π. The FP process can be proved via Groth 16 as described in [19,20,24], which is not the concern of this paper. To prove the validity of the training result, the BP process must be proposed, which is the process of chain rules as shown in Section 2.1.…”

Section: Zkp Proof Generation For the Local Training Processmentioning

confidence: 99%

TrustDFL: A Blockchain-Based Verifiable and Trusty Decentralized Federated Learning Framework

Yang,

Zhang,

Guo

et al. 2023

Electronics

View full text Add to dashboard Cite

Federated learning is a privacy-preserving machine learning framework where multiple data owners collaborate to train a global model under the orchestra of a central server. The local training results from trainers should be submitted to the central server for model aggregation and update. Busy central server and malicious trainers can introduce the issues of a single point of failure and model poisoning attacks. To address the above issues, the trusty decentralized federated learning (called TrustDFL) framework has been proposed in this paper based on the zero-knowledge proof scheme, blockchain, and smart contracts, which provides enhanced security and higher efficiency for model aggregation. Specifically, Groth 16 is applied to generate the proof for the local model training, including the forward and backward propagation processes. The proofs are attached as the payloads to the transactions, which are broadcast into the blockchain network and executed by the miners. With the support of smart contracts, the contributions of the trainers could be verified automatically under the economic incentive, where the blockchain records all exchanged data as the trust anchor in multi-party scenarios. In addition, IPFS (InterPlanetary File System) is introduced to alleviate the storage and communication overhead brought by local and global models. The theoretical analysis and estimation results show that the TrustDFL efficiently avoids model poisoning attacks without leaking the local secrets, ensuring the global model’s accuracy to be trained.

show abstract

Advancing Blockchain-based Federated Learning through Verifiable Off-chain Computations

Cited by 23 publications

References 25 publications

Federify: A Verifiable Federated Learning Scheme Based on zkSNARKs and Blockchain

Federify: A Verifiable Federated Learning Scheme Based on zkSNARKs and Blockchain

A Survey on Blockchain-Based Federated Learning: Categorization, Application and Analysis

TrustDFL: A Blockchain-Based Verifiable and Trusty Decentralized Federated Learning Framework

Contact Info

Product

Resources

About