Tag
#federated-learning
30 repositories
Repos
A curated list of awesome edge machine learning resources, including research papers, inference engines, challenges, books, meetups and others.
This project proposes a decentralized federated learning framework based on blockchain, that is, a Block-chain-based Federated Learning framework with Committee consensus (BFLC). Without a centralized server, the framework uses blockchain for the global model storage and the local model update exchange.
A scalable sharding solution for Blockchain based Federated Learning. SCaFL or ScaleSFL?
Programming Assignments and Quizzes from all courses within the Blockchain Specialization offered by The University at Buffalo and The State University of New York and key takeaways from study and research of myself. Besides, state of the arts in the field are also updated in this repository.
Federated learning on blockchain using smart contracts. Distributed privacy-preserving data science technology.
BEAS: Blockchain Enabled Asynchronous & Secure Federated Machine Learning
A notebook of awesome privacy protection,federated learning, fairness and blockchain research materials.
Privacy-preserving federated learning is distributed machine learning where multiple collaborators train a model through protected gradients. To achieve robustness to users dropping out, existing practical privacy-preserving federated learning schemes are based on (t, N)-threshold secret sharing. Such schemes rely on a strong assumption to guarantee security: the threshold t must be greater than half of the number of users. The assumption is so rigorous that in some scenarios the schemes may not be appropriate. Motivated by the issue, we first introduce membership proof for federated learning, which leverages cryptographic accumulators to generate membership proofs by accumulating users IDs. The proofs are issued in a public blockchain for users to verify. With membership proof, we propose a privacy-preserving federated learning scheme called PFLM. PFLM releases the assumption of threshold while maintaining the security guarantees. Additionally, we design a result verification algorithm based on a variant of ElGamal encryption to verify the correctness of aggregated results from the cloud server. The verification algorithm is integrated into PFLM as a part. Security analysis in a random oracle model shows that PFLM guarantees privacy against active adversaries. The implementation of PFLM and experiments demonstrate the performance of PFLM in terms of computation and communication.
High-scale Federated Learning (10M nodes) with formal BFT verification. Features 10ms zk-SNARKs and a 2026 PQC Overhaul: enforcing x25519-mlkem768 hybrid KEX, XMSS TPM-attestation, and epoch-based quantum-resistant ledger migration. Includes Go node agent + Python SDK v2.
Leveraging Federated Learning for Unsecured Loan Risk Assessment on Decentralized Finance Lending Platforms
Scoria AI is a decentralized AI agent framework on blockchain, enabling private, on-device Web3 intelligence for users and enterprises.
Scatter Protocol: An Incentivized and Trustless Protocol for Decentralized Federated Learning - Accepted to IEEE International Conference on Blockchain
Privacy-first decentralized AI training network combining federated learning, blockchain incentives, and quantum-safe cryptography. Enable secure collaborative model development without sharing raw data.
Scoria AI is a decentralized AI agent framework on blockchain, enabling private, on-device Web3 intelligence for users and enterprises.
This repository implements a peer-to-peer decentralized topology & a reputation-based tier system. It leverages federated learning for AI model training. Using DHT for peer discovery, proof-of-stake for voting, and multi-agent systems for model updates. With blockchain for tokenomics and smart contracts, providing a robust AGI Dev framework .
Privacy-preserving federated AI training system with blockchain governance and token rewards.
Amazon Rose Forest is the foundational codebase of FLOSSI0ULLK: a decentralized, agent-centric ecosystem for infinite overflowing unconditional love, light, and knowledge. It integrates Holochain, CRDTs, federated AI, and participatory governance to realize living collective intelligence and empower universal flourishing. All are welcome~~~!
Build a decentralized AI infrastructure on Solana, enabling secure on-chain model training and creating a global marketplace for AI inference services.
This work is part of 6GDAWN project for trust PoC. We use blockchain and smart contracts to enable a trustworthy reputation mechanism for O-RAN.