Chained Attacks on Drone-Based Federated Learning: From Network Disruption to Device Impersonation

2026-07-22

AI Summary

This study addresses the compounded vulnerability of unmanned aerial vehicle (UAV) federated learning systems to network disruptions and identity spoofing, a critical gap overlooked by existing approaches that fail to jointly consider availability and authentication. For the first time, it reveals the cascading effect between IEEE 802.11 deauthentication attacks and credential impersonation, formulating a chained attack model. Empirical evaluation on Raspberry Pi and Jetson platforms using the Flower framework demonstrates how wireless interruptions induce training instability and facilitate malicious node replacement. The work quantifies the amplified perturbation caused by brief disconnections on model convergence under non-independent and identically distributed (Non-IID) data and validates that an adversary can seamlessly hijack offline nodes through single-factor authentication flaws, exposing significant security deficiencies in current deployments within dynamic, heterogeneous environments.

Abstract

Edge Intelligence (EI) has emerged as a transformative model for mission-critical unmanned platforms, such as drone swarms, by enabling collaborative model training at the network periphery. However, the security of FL deployments depends on both network availability and robust client authentication mechanisms. This paper investigates a chained attack against drone-based FL systems that combines network-layer denial-of-service with credential-based impersonation. We demonstrate that an adversary can: (1) force legitimate drones offline using 802.11 deauthentication attacks, and (2) subsequently impersonate the disconnected drone using extracted credentials. Through a systematic literature review and empirical validation using the Flower framework on two distinct testbeds of Raspberry Pi and Jetsons, we quantify the impact of availability disruptions under Independent and Identically Distributed (IID) and Non-Independently and Identically Distributed (Non-IID) data distributions, and confirm that single-factor authentication permits post-disconnect impersonation. Our findings reveal that even short-term wireless interruptions cascade into substantial training instability, particularly under non-IID conditions, while the authentication gap enables adversaries to seamlessly replace disconnected nodes. We discuss the compounded implications for mission-critical drone deployments and outline directions for future defenses addressing both availability and authentication vulnerabilities.

Problem

• Federated Learning
• Drone Security
• Chained Attacks
• Authentication Vulnerability
• Network Disruption

Innovation

• chained attack
• federated learning
• drone swarm
• device impersonation
• edge intelligence