Decentralized Cross-Network Identity Management for Blockchain Interoperation

Ghosh, Bishakh Chandra; Venkatraman, R.; Govindarajan, Chander; Behl, Dushyant; Karunamoorthy, Dileban; Abebe, Ermyas; Chakraborty, Sandip

doi:10.1109/icbc51069.2021.9461064

Cited by 11 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1, one of the hospitals in the Hospitals' network and one of the diagnostic centers in the Diagnostic Centers' network can establish this relay communication to exchange the most updated learning assets between the two networks. We assume the existence of an Identity Interoperable Network (IIN) as a blockchain service similar to [38], which helps the clients to access the identity (public key) of the other clients in a different network. Based on the identity information, client In response to the transaction against a cross-chain access request, the blockchain B 2 triggers a local service (a smart contract).…”

Section: A Transfer Protocol -Asset Exchangementioning

confidence: 99%

Proof of Federated Training: Accountable Cross-Network Model Training and Inference

Chakraborty¹,

Chakraborty²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Blockchain has widely been adopted to design accountable federated learning frameworks; however, the existing frameworks do not scale for distributed model training over multiple independent blockchain networks. For storing the pretrained models over blockchain, current approaches primarily embed a model using its structural properties that are neither scalable for cross-chain exchange nor suitable for cross-chain verification. This paper proposes an architectural framework for cross-chain verifiable model training using federated learning, called Proof of Federated Training (PoFT), the first of its kind that enables a federated training procedure span across the clients over multiple blockchain networks. Instead of structural embedding, PoFT uses model parameters to embed the model over a blockchain and then applies a verifiable model exchange between two blockchain networks for cross-network model training. We implement and test PoFT over a large-scale setup using Amazon EC2 instances and observe that cross-chain training can significantly boosts up the model efficacy. In contrast, PoFT incurs marginal overhead for inter-chain model exchanges.

show abstract

Section: A Transfer Protocol -Asset Exchangementioning

confidence: 99%