mlsanityData to 13 Oct 2026

Poisoning Attacks on Federated Learning-based Wireless Traffic Prediction

arXiv 2404.14389 ↗First posted 22 Apr 2024cs.NI cs.CR cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) offers a distributed framework to train a global control model across multiple base stations without compromising the privacy of their local network data. This makes it ideal for applications like wireless traffic prediction (WTP), which plays a crucial role in optimizing network resources, enabling proactive traffic flow management, and enhancing the reliability of downstream communication-aided applications, such as IoT devices, autonomous vehicles, and industrial automation systems. Despite its promise, the security aspects of FL-based distributed wireless systems, particularly in regression-based WTP problems, remain inadequately investigated. In this paper, we introduce a novel fake traffic injection (FTI) attack, designed to undermine the FL-based WTP system by injecting fabricated traffic distributions with minimal knowledge. We further propose a defense mechanism, termed global-local inconsistency detection (GLID), which strategically removes abnormal model parameters that deviate beyond a specific percentile range estimated through statistical methods in each dimension. Extensive experimental evaluations, performed on real-world wireless traffic datasets, demonstrate that both our attack and defense strategies significantly outperform existing baselines.

Key facts. Cited by 10 papers in the map (data through 13 Oct 2026). Builds on 16 of its 32 references that are in the map. First posted on arXiv 22 Apr 2024.

Builds on

16 of 32 references.

References · 16

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,653
  2. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 708
  3. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 490
  4. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 339
  5. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  6. 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 251
  7. 2021Federated Learning for Smart Healthcare: A Surveycited by 183
  8. 2018Mitigating Sybils in Federated Learning Poisoningcited by 160
  9. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 139
  10. 2020Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challengescited by 139
  11. 2022MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clientscited by 68
  12. 2022AFLGuard: Byzantine-robust Asynchronous Federated Learningcited by 29
4 more
  1. 2021Dual Attention-Based Federated Learning for Wireless Traffic Predictioncited by 18
  2. 2024Poisoning Federated Recommender Systems with Fake Userscited by 15
  3. 2024Robust Federated Learning Mitigates Client-side Training Data Distribution Inference Attackscited by 11
  4. 2015A Review of Network Traffic Analysis and Prediction Techniquescited by 4

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 3.

10 papers.

  1. 2024Byzantine-Robust Decentralized Federated Learningcited by 48
  2. 2025Traceback of Poisoning Attacks to Retrieval-Augmented Generationcited by 28
  3. 2025Do We Really Need to Design New Byzantine-robust Aggregation Rules?cited by 15
  4. 2025Provably Robust Federated Reinforcement Learningcited by 8
  5. 2025Poisoning Attacks and Defenses to Federated Unlearningcited by 5
  6. 2025Toward Malicious Clients Detection in Federated Learningcited by 4
  7. 2025Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated Learningcited by 1
  8. 2026When the Server Steps In: Calibrated Updates for Fair Federated Learningcited by 0
  9. 2026SecureAFL: Secure Asynchronous Federated Learningcited by 0
  10. 2026Securing Autonomous Vehicle Systems via Twin-Aware Federated Reinforcement Learningcited by 0