# IronForge: An Open, Secure, Fair, Decentralized Federated Learning

arXiv: https://arxiv.org/abs/2301.04006 · HTML: https://mlsanity.com/paper/2301.04006/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 7 Jan 2023.

## Builds on (most cited first, 23 of 23)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [Robust and Communication-Efficient Federated Learning from Non-IID Data](https://mlsanity.com/paper/1903.02891/) (2019)
- [Analyzing Federated Learning through an Adversarial Lens](https://mlsanity.com/paper/1811.12470/) (2018)
- [Knockoff Nets: Stealing Functionality of Black-Box Models](https://mlsanity.com/paper/1812.02766/) (2018)
- [Asynchronous Federated Optimization](https://mlsanity.com/paper/1903.03934/) (2019)
- [Blockchained On-Device Federated Learning](https://mlsanity.com/paper/1808.03949/) (2018)
- [Collaborative Fairness in Federated Learning](https://mlsanity.com/paper/2008.12161/) (2020)
- [Reliable Federated Learning for Mobile Networks](https://mlsanity.com/paper/1910.06837/) (2019)
- [Proof-of-Learning: Definitions and Practice](https://mlsanity.com/paper/2103.05633/) (2021)
- [SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overhead](https://mlsanity.com/paper/1910.01355/) (2019)
- [Federated Learning Meets Blockchain in Edge Computing: Opportunities and Challenges](https://mlsanity.com/paper/2104.01776/) (2021)
- [Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Data](https://mlsanity.com/paper/1806.05476/) (2018)
- [A Secure Federated Learning Framework for 5G Networks](https://mlsanity.com/paper/2005.05752/) (2020)
- [When Federated Learning Meets Blockchain: A New Distributed Learning Paradigm](https://mlsanity.com/paper/2009.09338/) (2020)
- ["Adversarial Examples" for Proof-of-Learning](https://mlsanity.com/paper/2108.09454/) (2021)
- [ScaleSFL: A Sharding Solution for Blockchain-Based Federated Learning](https://mlsanity.com/paper/2204.01202/) (2022)
- [Dataset Obfuscation: Its Applications to and Impacts on Edge Machine Learning](https://mlsanity.com/paper/2208.03909/) (2022)
- [Towards On-Device Federated Learning: A Direct Acyclic Graph-based Blockchain Approach](https://mlsanity.com/paper/2104.13092/) (2021)

## Built on by (most cited first, 15 of 15)

- [Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Survey](https://mlsanity.com/paper/2312.08667/) (2023)
- [Noiseless Privacy-Preserving Decentralized Learning](https://mlsanity.com/paper/2404.09536/) (2024)
- [Advancements in Federated Learning: Models, Methods, and Privacy](https://mlsanity.com/paper/2302.11466/) (2023)
- [Blockchained Federated Learning for Internet of Things: A Comprehensive Survey](https://mlsanity.com/paper/2305.04513/) (2023)
- [Is Your AI Truly Yours? Leveraging Blockchain for Copyrights, Provenance, and Lineage](https://mlsanity.com/paper/2404.06077/) (2024)
- [Blockchain-Empowered Trustworthy Data Sharing: Fundamentals, Applications, and Challenges](https://mlsanity.com/paper/2303.06546/) (2023)
- [BlockFUL: Enabling Unlearning in Blockchained Federated Learning](https://mlsanity.com/paper/2402.16294/) (2024)
- [Smart Sampling: Helping from Friendly Neighbors for Decentralized Federated Learning](https://mlsanity.com/paper/2407.04460/) (2024)
- [Parallel Unlearning in Inherited Model Networks](https://mlsanity.com/paper/2408.08493/) (2024)
- [Carpe Diem: Critical Learning Period-Aware Contract-Based Incentives for Federated Learning](https://mlsanity.com/paper/2503.07869/) (2025)
- [ZK-HybridFL: Zero-Knowledge Proof-Enhanced Hybrid Ledger for Federated Learning](https://mlsanity.com/paper/2601.22302/) (2026)
- [Distributed Trust Through the Lens of Software Architecture](https://mlsanity.com/paper/2306.08056/) (2023)
- [Alpha and Prejudice: Improving α-sized Worst-case Fairness via Intrinsic Reweighting](https://mlsanity.com/paper/2411.03068/) (2024)
- [PoLO: Proof-of-Learning and Proof-of-Ownership at Once with Chained Watermarking](https://mlsanity.com/paper/2505.12296/) (2025)
- [Secure Decentralized Federated Learning via Gossip and Virtual Voting](https://mlsanity.com/paper/2607.08651/) (2026)

## Abstract (arXiv)

Federated learning (FL) provides an effective machine learning (ML) architecture to protect data privacy in a distributed manner. However, the inevitable network asynchrony, the over-dependence on a central coordinator, and the lack of an open and fair incentive mechanism collectively hinder its further development. We propose textscIronForge, a new generation of FL framework, that features a Directed Acyclic Graph (DAG)-based data structure and eliminates the need for central coordinators to achieve fully decentralized operations. textscIronForge runs in a public and open network, and launches a fair incentive mechanism by enabling state consistency in the DAG, so that the system fits in networks where training resources are unevenly distributed. In addition, dedicated defense strategies against prevalent FL attacks on incentive fairness and data privacy are presented to ensure the security of textscIronForge. Experimental results based on a newly developed testbed FLSim highlight the superiority of textscIronForge to the existing prevalent FL frameworks under various specifications in performance, fairness, and security. To the best of our knowledge, textscIronForge is the first secure and fully decentralized FL framework that can be applied in open networks with realistic network and training settings.