Unmanned aerial vehicles (UAVs) extend the traditional ground-based Internet of Things (IoT) into the air. UAV mobile edge computing (MEC) architectures have been proposed by integrating UAVs into MEC networks during the current novel coronavirus disease (COVID-19) era. UAV mobile edge computing (MEC) shares personal data with external parties (such as edge servers) during intelligent medical analytics. However, this technique raises privacy concerns about patients’ health data. More recently, the concept of federal learning (FL) has been set up to protect mobile user data privacy. Compared to traditional machine learning, federated learning requires a decentralized distribution system to enhance trust for UAVs. Blockchain technology provides a secure and reliable solution for FL settings between multiple untrusted parties with anonymous, immutable, and distributed features. Therefore, blockchain-enabled FL provides both theories and techniques to improve the performance of intelligent UAV edge computing networks from various perspectives. This survey begins by discussing the current state of research on blockchain and FL. Then, compare the leading technologies and limitations. Second, we will discuss how to integrate blockchain and FL into UAV edge computing networks and the associated challenges and solutions. Finally, we discuss the fundamental research challenges and future directions.

The widespread use of UAVs in smart cities for tasks like traffic monitoring and environmental data collection creates significant privacy and security concerns due to the transmission of sensitive data. Traditional UAV-MEC systems with centralized data processing expose this data to risks like breaches and manipulation, potentially hindering the adoption of these valuable technologies. To address this critical challenge, we propose UBFL, a novel privacy-preserving federated learning mechanism that integrates blockchain technology for secure and efficient data sharing. Unlike traditional methods relying on differential privacy (DP), UBFL employs an adaptive nonlinear encryption function to safeguard the privacy of UAV model updates while maintaining data integrity and accuracy. This innovative approach enables rapid convergence, allowing the base station to efficiently identify and filter out severely compromised UAVs attempting to inject malicious data. Additionally, UBFL incorporates the Random Cut Forest (RCF) anomaly detection algorithm to actively identify and mitigate poisoning data attacks. Extensive comparative experiments on benchmark datasets CIFAR10 and Mnist demonstrably showcase UBFL’s effectiveness. Compared to DP-based methods, UBFL achieves accuracy (99.98%), precision (99.93%), recall (99.92%), and F-Score (99.92%) in privacy preservation while maintaining superior accuracy. Notably, under data pollution scenarios with varying attack sample rates (10%, 20%, and 30%), UBFL exhibits exceptional resilience, highlighting its robust capabilities in securing UAV gradients within MEC environments.

The UAV (unmanned aerial vehicles) network is a promising solution to support real-time applications and services. However, local UAV nodes are prone to privacy disclosure, and base station edge nodes are difficult to effectively identify trusted local UAV nodes and resist malicious attacks. To address the privacy concern, we propose the adaptive nonlinear privacy protection to preserve model gradient in the federated learning training process, overcoming the drawbacks associated with empirically selecting DP(Differential privacy) parameters. Through the model accuracy analysis, it can be seen that the proposed algorithm achieves higher accuracy in privacy protection using adaptive layered contribution factor compared with the privacy protection method based on DP.Experiments show that the proposed algorithm can effectively protect the privacy and security of UAV gradient, and achieve higher accuracy. Under the conditions of 10%, 20% and 30% pollution ratio of data sets, the experiment shows that the proposed algorithm still has strong anti-data poisoning attack ability.

Cooperative multi‐agent reinforcement learning (CMARL) has become a powerful paradigm for applications in autonomous driving, smart grids, and distributed robotics. However, its increasing adoption in safety‐critical scenarios raises severe concerns about security vulnerabilities, particularly backdoor attacks, where malicious behaviors are embedded and activated only under specific triggers. This paper presents TReS‐BD, a trigger‐aware reward shaping framework that systematically exploits CMARL vulnerabilities at the reward level. By formulating backdoor manipulation as a Bayes‐Adaptive Markov Decision Process (BAMDP), TReS‐BD treats trigger conditions as latent variables and integrates KL‐regularized policy optimization to maintain nominal task performance while inducing adversarial behaviors under triggers. Extensive experiments on standard benchmarks, including multi‐agent particle environments (MPE) and StarCraft Multi‐Agent Challenge (SMAC), with representative algorithms MADDPG and MAPPO, demonstrate that TReS‐BD achieves over 90% attack success with less than 1% training data poisoning, while maintaining normal performance and evading current detection mechanisms. Furthermore, a systematic analysis of existing defenses reveals their ineffectiveness against such reward‐level attacks, underscoring a critical blind spot in current CMARL security frameworks. Our findings highlight the urgent need for robust defense strategies and provide new insights into safeguarding cooperative multi‐agent systems against stealthy and efficient backdoor threats.