# Trustless Federated Learning at Edge-Scale: A Compositional Architecture for Decentralized, Verifiable, and Incentive-Aligned Coordination

arXiv: https://arxiv.org/abs/2511.21118 · HTML: https://mlsanity.com/paper/2511.21118/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 37 references that are in the map.
- First posted on arXiv 26 Nov 2025.

## Builds on (most cited first, 13 of 13)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [Federated Learning Meets Blockchain in Edge Computing: Opportunities and Challenges](https://mlsanity.com/paper/2104.01776/) (2021)
- [IPFS - Content Addressed, Versioned, P2P File System](https://mlsanity.com/paper/1407.3561/) (2014)
- [Blockchain Assisted Decentralized Federated Learning (BLADE-FL): Performance Analysis and Resource Allocation](https://mlsanity.com/paper/2101.06905/) (2021)
- [A Review of zk-SNARKs](https://mlsanity.com/paper/2202.06877/) (2022)
- [Mean Aggregator is More Robust than Robust Aggregators under Label Poisoning Attacks on Distributed Heterogeneous Data](https://mlsanity.com/paper/2404.13647/) (2024)
- [ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning](https://mlsanity.com/paper/2405.20975/) (2024)
- [Narwhal and Tusk: A DAG-based Mempool and Efficient BFT Consensus](https://mlsanity.com/paper/2105.11827/) (2021)

## Abstract (arXiv)

Artificial intelligence is retracing the Internet's path from centralized provision to distributed creation. Initially, resource-intensive computation concentrates within institutions capable of training and serving large models.Eventually, as federated learning matures, billions of edge devices holding sensitive data will be able to collectively improve models without surrendering raw information, enabling both contribution and consumption at scale. This democratic vision remains unrealized due to certain compositional gaps; aggregators handle updates without accountability, economic mechanisms are lacking and even when present remain vulnerable to gaming, coordination serializes state modifications limiting scalability, and governance permits retroactive manipulation. This work addresses these gaps by leveraging cryptographic receipts to prove aggregation correctness, geometric novelty measurement to prevent incentive gaming, parallel object ownership to achieve linear scalability, and time-locked policies to check retroactive manipulation.