Scatter Protocol: An Incentivized and Trustless Protocol for Decentralized Federated Learning
Author(s)
Sahoo, Samrat
Advisor(s)
Editor(s)
Collections
Supplementary to:
Permanent Link
Abstract
Federated Learning is a form of privacy-preserving machine learning where multiple entities train local models which are then aggregated into a global model. Current forms of federated learning rely on a centralized server to orchestrate the process, leading to issues such as requiring trust in the orchestrator, the necessity of a middleman, and a single point of failure. Blockchains provide a way to record information on a transparent, distributed ledger accessible and verifiable by any entity. We leverage these properties of blockchains to produce a decentralized, federated learning marketplace-style protocol for training models collaboratively. Our core contributions are as follows: first, we introduce novel staking, incentivization, and penalization mechanisms to deter malicious nodes and encourage benign behavior. Second, we introduce a dual-faceted lottery-based validation layer to ensure the authenticity of the models trained. Third, we test different components of our system to verify sufficient incentivization, penalization, and resistance to malicious attacks.
Sponsor
Date
Extent
Resource Type
Text
Resource Subtype
Undergraduate Research Option Thesis