mlsanityData to 14 Oct 2026

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

arXiv 2210.11061 ↗First posted 20 Oct 2022cs.LGcited by 2

On the map: LLM safety and security → Federated unlearning and poisoning

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.

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.

Builds on

20 of 39 references.

References · 20

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Deep Leakage from Gradientscited by 1,021
  3. 2019Federated Machine Learning: Concept and Applicationscited by 412
  4. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  5. 2019Robust Aggregation for Federated Learningcited by 317
  6. 2020Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defensescited by 180
  7. 2020Threats to Federated Learning: A Surveycited by 178
  8. 2019SecureBoost: A Lossless Federated Learning Frameworkcited by 176
  9. 2018Mitigating Sybils in Federated Learning Poisoningcited by 161
  10. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 106
  11. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 84
  12. 2020SplitNN-driven Vertical Partitioningcited by 42
8 more
  1. 2021PipAttack: Poisoning Federated Recommender Systems forManipulating Item Promotioncited by 37
  2. 2021Federated Learning for Malware Detection in IoT Devicescited by 36
  3. 2019A Communication Efficient Collaborative Learning Framework for Distributed Featurescited by 21
  4. 2021A Decentralized Federated Learning Framework via Committee Mechanism with Convergence Guaranteecited by 16
  5. 2021Efficient Client Contribution Evaluation for Horizontal Federated Learningcited by 13
  6. 2020GFL: A Decentralized Federated Learning Framework Based On Blockchaincited by 12
  7. 2021Efficient Ring-topology Decentralized Federated Learning with Deep Generative Models for Industrial Artificial Intelligentcited by 5
  8. 2022Studying the Robustness of Anti-adversarial Federated Learning Models Detecting Cyberattacks in IoT Spectrum Sensorscited by 5

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 1.

2 papers.

  1. 2022Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challengescited by 138
  2. 2024De-VertiFL: A Solution for Decentralized Vertical Federated Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Towards Understanding Quality Challenges of the Federated Learning for Neural Networks: A First Look from the Lens of Robustness
  2. 2023BadVFL: Backdoor Attacks in Vertical Federated Learning
  3. 2024Byzantine-Robust Federated Learning: An Overview With Focus on Developing Sybil-based Attacks to Backdoor Augmented Secure Aggregation Protocols
  4. 2024Security Assessment of Hierarchical Federated Deep Learning
  5. 2026BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning
  6. 2023Security and Privacy Issues of Federated Learning
  7. 2025Towards Communication-Efficient Adversarial Federated Learning for Robust Edge Intelligence
  8. 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attacks