# Analyzing the Robustness of Decentralized Horizontal and Vertical Federated Learning Architectures in a Non-IID Scenario

arXiv: https://arxiv.org/abs/2210.11061 · HTML: https://mlsanity.com/paper/2210.11061/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security.
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 20 Oct 2022.

## Placed in

- LLM safety and security / [Federated unlearning and poisoning](https://mlsanity.com/safety/federated-unlearning-and-poisoning/)

## Builds on (most cited first, 20 of 20)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Federated Machine Learning: Concept and Applications](https://mlsanity.com/paper/1902.04885/) (2019)
- [Analyzing Federated Learning through an Adversarial Lens](https://mlsanity.com/paper/1811.12470/) (2018)
- [Robust Aggregation for Federated Learning](https://mlsanity.com/paper/1912.13445/) (2019)
- [Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses](https://mlsanity.com/paper/2012.10544/) (2020)
- [Threats to Federated Learning: A Survey](https://mlsanity.com/paper/2003.02133/) (2020)
- [SecureBoost: A Lossless Federated Learning Framework](https://mlsanity.com/paper/1901.08755/) (2019)
- [Mitigating Sybils in Federated Learning Poisoning](https://mlsanity.com/paper/1808.04866/) (2018)
- [Feature Inference Attack on Model Predictions in Vertical Federated Learning](https://mlsanity.com/paper/2010.10152/) (2020)
- [Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges](https://mlsanity.com/paper/2201.08135/) (2022)
- [SplitNN-driven Vertical Partitioning](https://mlsanity.com/paper/2008.04137/) (2020)
- [PipAttack: Poisoning Federated Recommender Systems forManipulating Item Promotion](https://mlsanity.com/paper/2110.10926/) (2021)
- [Federated Learning for Malware Detection in IoT Devices](https://mlsanity.com/paper/2104.09994/) (2021)
- [A Communication Efficient Collaborative Learning Framework for Distributed Features](https://mlsanity.com/paper/1912.11187/) (2019)
- [A Decentralized Federated Learning Framework via Committee Mechanism with Convergence Guarantee](https://mlsanity.com/paper/2108.00365/) (2021)
- [Efficient Client Contribution Evaluation for Horizontal Federated Learning](https://mlsanity.com/paper/2102.13314/) (2021)
- [GFL: A Decentralized Federated Learning Framework Based On Blockchain](https://mlsanity.com/paper/2010.10996/) (2020)
- [Efficient Ring-topology Decentralized Federated Learning with Deep Generative Models for Industrial Artificial Intelligent](https://mlsanity.com/paper/2104.08100/) (2021)
- [Studying the Robustness of Anti-adversarial Federated Learning Models Detecting Cyberattacks in IoT Spectrum Sensors](https://mlsanity.com/paper/2202.00137/) (2022)

## Built on by (most cited first, 2 of 2)

- [Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges](https://mlsanity.com/paper/2211.08413/) (2022)
- [De-VertiFL: A Solution for Decentralized Vertical Federated Learning](https://mlsanity.com/paper/2410.06127/) (2024)

## Abstract (arXiv)

Federated learning (FL) allows participants to collaboratively train machine and deep learning models while protecting data privacy. However, the FL paradigm still presents drawbacks affecting its trustworthiness since malicious participants could launch adversarial attacks against the training process. Related work has studied the robustness of horizontal FL scenarios under different attacks. However, there is a lack of work evaluating the robustness of decentralized vertical FL and comparing it with horizontal FL architectures affected by adversarial attacks. Thus, this work proposes three decentralized FL architectures, one for horizontal and two for vertical scenarios, namely HoriChain, VertiChain, and VertiComb. These architectures present different neural networks and training protocols suitable for horizontal and vertical scenarios. Then, a decentralized, privacy-preserving, and federated use case with non-IID data to classify handwritten digits is deployed to evaluate the performance of the three architectures. Finally, a set of experiments computes and compares the robustness of the proposed architectures when they are affected by different data poisoning based on image watermarks and gradient poisoning adversarial attacks. The experiments show that even though particular configurations of both attacks can destroy the classification performance of the architectures, HoriChain is the most robust one.