mlsanityData to 14 Oct 2026

Targeted Attacks and Defenses for Distributed Federated Learning in Vehicular Networks

arXiv 2510.15109 ↗First posted 16 Oct 2025cs.NI cs.AI cs.DCcited by 0

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

Abstract (arXiv)

In emerging networked systems, mobile edge devices such as ground vehicles and unmanned aerial system (UAS) swarms collectively aggregate vast amounts of data to make machine learning decisions such as threat detection in remote, dynamic, and infrastructure-constrained environments where power and bandwidth are scarce. Federated learning (FL) addresses these constraints and privacy concerns by enabling nodes to share local model weights for deep neural networks instead of raw data, facilitating more reliable decision-making than individual learning. However, conventional FL relies on a central server to coordinate model updates in each learning round, which imposes significant computational burdens on the central node and may not be feasible due to the connectivity constraints. By eliminating dependence on a central server, distributed federated learning (DFL) offers scalability, resilience to node failures, learning robustness, and more effective defense strategies. Despite these advantages, DFL remains vulnerable to increasingly advanced and stealthy cyberattacks. In this paper, we design sophisticated targeted training data poisoning and backdoor (Trojan) attacks, and characterize the emerging vulnerabilities in a vehicular network. We analyze how DFL provides resilience against such attacks compared to individual learning and present effective defense mechanisms to further strengthen DFL against the emerging cyber threats.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 11 of its 22 references that are in the map. First posted on arXiv 16 Oct 2025.

Builds on

11 of 22 references.

References · 11

  1. 2020Federated Learning in Vehicular Networkscited by 53
  2. 2019Trojan Attacks on Wireless Signal Classification with Adversarial Machine Learningcited by 15
  3. 2022Vulnerabilities of Deep Learning-Driven Semantic Communications to Backdoor (Trojan) Attackscited by 10
  4. 2022Federated Learning for Distributed Spectrum Sensing in NextG Communication Networkscited by 7
  5. 2022Jamming Attacks on Federated Learning in Wireless Networkscited by 6
  6. 2024Provable Privacy Advantages of Decentralized Federated Learning via Distributed Optimizationcited by 6
  7. 2023Jamming Attacks on Decentralized Federated Learning in General Multi-Hop Wireless Networkscited by 4
  8. 2023Federated Learning-based Vehicle Trajectory Prediction against Cyberattackscited by 3
  9. 2023Hidden Backdoor Attack against Deep Learning-Based Wireless Signal Modulation Classifierscited by 2
  10. 2023Securing NextG Systems against Poisoning Attacks on Federated Learning: A Game-Theoretic Solutioncited by 2
  11. 2025Distributed Federated Learning for Vehicular Network Security: Anomaly Detection Benefits and Multi-Domain Attack Threatscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning
  2. 2022Invariant Aggregator for Defending against Federated Backdoor Attacks
  3. 2023A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective
  4. 2026A Secure and Private Distributed Bayesian Federated Learning Design
  5. 2024Byzantine-Robust Federated Learning: An Overview With Focus on Developing Sybil-based Attacks to Backdoor Augmented Secure Aggregation Protocols
  6. 2025SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
  7. 2024Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning
  8. 2023FedDefender: Backdoor Attack Defense in Federated Learning