Federated learning coordinates model training in a distributed manner within Internet of Things (IoT) systems and ensures the privacy of local client data simultaneously. Nonetheless, traditional federated learning relies primarily on a unified global model and focuses on local feature extraction, failing to accommodate the diversity and personalized needs of clients in non-independent and identically distributed (non-IID) environments. To mitigate the decline in model accuracy posed by these challenges, we propose a discrepancy-aware federated learning method based on multi-branch feature fusion (FedDM). Firstly, we design a differential-aware aggregation strategy (DA), which adjusts the contribution of each client during model aggregation using Gaussian distribution statistics, to generate personalized local models. Next, we propose a multi-branch feature fusion mechanism (MFF) that integrates diverse feature representations through multi-scale pooling and feature enhancement, enabling the incorporation of features across both spatial and channel dimensions for a more holistic representation. Experimental results demonstrate that FedDM enhances model accuracy and robustness, while exhibiting adaptability when facing challenges posed by data distribution heterogeneity.
Federated learning (FL) utilizes distributed data processing to enable collaborative machine learning model development while safeguarding user privacy. However, the decentralized nature of FL, combined with data heterogeneity, substantially expands the attack surface for backdoor threats. Existing FL attack and defense strategies typically target the entire model, neglecting the critical backdoor parameters—a small subset of parameters that govern model vulnerabilities. Focusing on these parameters can replicate the impact of attacking the entire model while greatly reducing the risk of detection by advanced defenses. To address this challenge, we introduce Key Parameter Backdoor Attack in Federated Learning (KPBAFL), an innovative, adaptive, and scalable framework specifically designed to exploit model vulnerabilities by targeting critical backdoor parameters. KPBAFL integrates three core components: key parameter analysis, a beacon feedback mechanism, and adaptive attack strategies. By embedding beacons within the backdoor model, the framework can gather real-time attack feedback and dynamically adjust its strategy accordingly. When these components operate in concert, KPBAFL exhibits exceptional stealthiness, achieving an attack success rate (ASR) exceeding 96.5% while maintaining a benign task accuracy (BTA) of 97.8% across various datasets and models. Extensive experiments demonstrate its effectiveness, even in the presence of advanced defenses such as FLAME, Fldetector, Rflbat, and Deepsight, underscoring its strong generalizability. Although the modular design ensures adaptability, the framework’s performance may significantly degrade if the components are not properly synchronized. Our research provides a critical foundation for understanding and mitigating backdoor vulnerabilities in federated learning systems.
With the aggravation of global warming, drought has caused more and more serious impact on society and national economy, so the accurate prediction of drought is also the most important thing to deal with the frequent drought problem. On the other hand, artificial intelligence technology has shown its advantages in various fields and has a broad application prospects, so it is gradually being used in drought prediction. In this paper, drought prediction algorithms in recent years are reviewed, and existing cases of drought prediction using different arithmetic models for different drought indices are studied. The advantages and disadvantages of different algorithms are compared, the challenges of drought prediction are summarized, and the future of drought prediction is prospected.
To address the challenges faced in detecting malicious vehicles on the Internet of Vehicles, as well as the limitations of utilizing positive and negative response frequencies to adjust reputation values and the loss of independent judgment when relying on vehicle location and time data, a trust management mechanism based on non-cooperative game theory is proposed. This mechanism aims to identify malicious vehicles by evaluating whether their strategies satisfy utility functions. By incorporating both positive and negative interaction frequencies and historical trust data, the mechanism successfully resolves the issue of malicious vehicle switch attacks while ensuring a stable increase in reputation values. Simulation results demonstrate the effectiveness of the proposed approach in accurately detecting switch attacks by malicious vehicles and its strong resilience against slander attacks.