The widespread use of Unmanned Aerial Vehicles (UAV) has made the security and computing resource application efficiency of UAV a hot topic in the security field of the Internet of Things. In this paper, an optimized lightweight identity security authentication protocol, Optimized Identity Authentication Protocol (ODIAP) is proposed for Internet of Drones (IoD) networks. The protocol is targeted to the security risks faced by IoD networks, and proposes the security authentication mechanism consisting of 3 phases and 7 authentication processes, which enables the protocol has both forward and backward security, and can resist mainstream network attacks. Meanwhile, this paper fully considers the computational load and proposes the identity information generation and verification method based on the Chinese residual theorem, which reduces the computational load of resource-constrained nodes and shifts the complex computational process to server nodes with abundant computational resources. Moreover, after security protocol analysis and tool verification based on the automated security verification tool Proverif, the protocol in this paper has complete security. At the same time, the performance analysis and comparison with other mainstream protocols shows that this protocol effectively optimizes the use of computing resources without compromising security.

The Internet of Vehicles (IoV) is an interactive network providing intelligent traffic management, intelligent dynamic information service, and intelligent vehicle control to running vehicles. One of the main problems in the IoV is the reluctance of vehicles to share local data resulting in the cloud server not being able to acquire a sufficient amount of data to build accurate machine learning (ML) models. In addition, communication efficiency and ML model accuracy in the IoV are affected by noise data caused by violent shaking and obscuration of in-vehicle cameras. Therefore we propose a new Outlier Detection and Exponential Smoothing federated learning (OES-Fed) framework to overcome these problems. More specifically, we filter the noise data of the local ML model in the IoV from the current perspective and historical perspective. The noise data filtering is implemented by combining data outlier, K-means, Kalman filter and exponential smoothing algorithms. The experimental results of the three datasets show that the OES-Fed framework proposed in this article achieved higher accuracy, lower loss, and better area under the curve (AUC). The OES-Fed framework we propose can better filter noise data, providing an important domain reference for starting field of federated learning in the IoV.

With the rapid increase of data, centralized machine learning can no longer meet the application requirements of the Internet of Vehicles (IoV). On the one hand, both car owners and regulators pay more attention to data privacy and are unwilling to share data, which forms the isolated data island challenge. On the other hand, the incremental data generated in IoV are massive and diverse. All these issues have brought challenges of data increment and data diversity. The current common federated learning or incremental learning frameworks cannot effectively integrate incremental data with existing machine learning (ML) models. Therefore, this paper proposes a Federated Learning Framework Based on Incremental Weighting and Diversity Selection for IoV (Fed-IW&DS). In Fed-IW&DS, a vehicle diversity selection algorithm was proposed, which uses a variety of performance indicators to calculate diversity scores, effectively reducing homogeneous computing. Also, it proposes a vehicle federated incremental algorithm that uses an improved arctangent curve as the decay function, to realize the rapid fusion of incremental data with existing ML models. Moreover, we have carried out several sets of experiments to test the validity of the proposed Fed-IW&DS framework’s performance. The experimental results show that, under the same global communication round and similar computing time, the Fed-IW&DS framework has significantly improved performance in all aspects compared to the frameworks FED-AVG, FED-SGD, FED-prox & the decay functions linear, square curve and arc tangent. Specifically, the Fed-IW&DS framework improves the Acc (accuracy), loss (loss), and Matthews correlation coefficient (MCC) by approximately 32%, 83%, and 66%, respectively. This result shows that Fed-IW&DS is a more reliable solution than the common frameworks of federated learning, and it can effectively deal with the dynamic incremental data in the IoV scenario. Our findings should make a significant contribution to the field of federated learning.

The rise of targeted advertising has led to frequent privacy data leaks, as advertisers are reluctant to share information to safeguard their interests. This has resulted in isolated data islands and model heterogeneity challenges. To address these issues, we have proposed a C-means clustering algorithm based on maximum average difference to improve the evaluation of the difference in distribution between local and global parameters. Additionally, we have introduced an innovative dynamic selection algorithm that leverages knowledge distillation and weight correction to reduce the impact of model heterogeneity. Our framework was tested on various datasets and its performance was evaluated using accuracy, loss, and AUC (area under the ROC curve) metrics. Results showed that the framework outperformed other models in terms of higher accuracy, lower loss, and better AUC while requiring the same computation time. Our research aims to provide a more reliable, controllable, and secure data sharing framework to enhance the efficiency and accuracy of targeted advertising.

In the realm of targeted advertising, the demand for precision is paramount, and the traditional centralized machine learning paradigm fails to address this necessity effectively. Two critical challenges persist in the current advertising ecosystem: the data privacy concerns leading to isolated data islands and the complexity in handling non-Independent and Identically Distributed (non-IID) data and concept drift due to the specificity and diversity in user behavior data. Current federated learning frameworks struggle to overcome these hurdles satisfactorily. This paper introduces Fed-GANCC, an innovative federated learning framework that synergizes Generative Adversarial Networks (GANs) and Group Clustering. The framework incorporates a user data augmentation algorithm predicated on adversarial generative networks to enrich user behavior data, curtail the impact of non-uniform data distribution, and enhance the applicability of the global machine learning model. Unlike traditional approaches, our framework offers user data augmentation algorithms based on adversarial generative networks, which not only enriches user behavior data but also reduces the challenges posed by non-uniform data distribution, thereby enhancing the applicability of the global machine learning (ML) model. The effectiveness of Fed-GANCC is distinctly showcased through experimental results, outperforming contemporary methods like FED-AVG and FED-SGD in terms of accuracy, loss value, and receiver operating characteristic (ROC) indicators within the same computing time. Experimental results vindicate the effectiveness of Fed-GANCC, revealing substantial enhancements in accuracy, loss value, and receiver operating characteristic (ROC) metrics compared to FED-AVG and FED-SGD given the same computational time. These outcomes underline Fed-GANCC’s exceptional prowess in mitigating issues such as isolated data islands, non-IID data, and concept drift. With its novel approach to addressing the prevailing challenges in targeted advertising such as isolated data islands, non-IID data, and concept drift, the Fed-GANCC framework stands as a benchmark, paving the way for future advancements in federated learning solutions tailored for the advertising domain. The Fed-GANCC framework promises to offer pivotal insights for the future development of efficient and advanced federated learning solutions for targeted advertising.

With the increasing challenges of default risk in the auto loan market, traditional risk assessment methods show significant limitations in coping with the rapidly changing market environment. This study proposes an innovative deep learning architecture—Deep Capsule Attention Network (DECAF)—which integrates capsule networks with self-attention mechanisms, effectively enhancing the intelligent detection capability for auto loan default risks. Experimental evaluations of the model’s performance in both conventional and high-risk scenarios demonstrate that the DECAF model achieved an area under the curve (AUC) of 0.924 in the conventional scenario and maintained a high performance of 0.850 in high-risk scenarios. Additionally, DECAF exhibits a significant advantage in terms of reducing false positives (FPR < 0.2), effectively minimizing misjudgments. More importantly, the study reveals that the DECAF model retains high stability even under severe market fluctuations, with only a 7.4% performance drop. These results provide new insights and solutions for financial institutions to optimize risk control strategies in dynamic market environments.