Equinix是全球领先的数据运营商,目前在美洲、亚太、欧洲及中东14 个国家(地区)的31 个市场运营着94个国际业务交换。
Grid cybersecurity has a data-sharing problem. Training a good intrusion detection model needs measurements from multiple nodes — but those nodes belong to different operators who will not share raw operational data with each other. Federated learning is the standard answer: train locally, share only model weights, aggregate centrally. The question nobody has answered on real microgrid data is how much detection performance you actually give up by doing it that way. This paper runs that experiment on real measurements from the Mafate isolated microgrid on Réunion Island — 89,179 temporally aligned records split across three simulated federated client nodes. One node gets solar plant measurements. Two nodes get demand-side measurements. Four attack types — scaling, ramp, bias, and replay-bias — are injected at different rates per client, reflecting the non-IID conditions that make federated learning hard. Multi-Layer Perceptron models train locally for five epochs per round, then aggregate via Federated Averaging across ten communication rounds. The federated global model hit 83.79% accuracy, 72.37% F1-score, and 92.97% AUC-ROC. Global F1 grew from 59.76% at round one to 72.37% by round ten — slow, but sure people! The centralized trained on the same data scored an F1 of 99.43%. That gap is the cost of privacy on this dataset, under those conditions — a percentage-point difference of 27.06 when the maximal condition is satisfied. It is not concealed or rationalized — it is the number that this paper was created to quantify.
The rapid proliferation of Internet of Things (IoT) devices has increased vulnerability of large-scale IoT networks to botnet attacks, which compromise resource-constrained devices and perform coordinated malicious activities. However, conventional botnet detection approaches often depend on centralized data collection, resulting in privacy risks, high communication overhead, and limited adaptability to heterogeneous network environments. To address these challenges, Federated Trust-Consistency Learning Network (FTCLN) is proposed for botnet detection without direct transfer of raw local traffic. Initially, N-BaIoT dataset is considered, and robust quantile normalization is applied to reduce the influence of highly skewed network traffic and heterogeneous feature distributions. Subsequently, Temporal Dilated Convolutional Feature Extraction (TDCFE) is employed to capture local and long-range temporal dependencies from IoT traffic patterns. Furthermore, federated learning is incorporated to train distributed detection models without transferring raw network traffic. A Trust-Consistency Principle (TCP) evaluates client updates based on prototype consistency and optimization-direction agreement, enabling reliable aggregation of heterogeneous client models. The resulting global model accurately distinguishes benign and botnet traffic while reducing influence of inconsistent updates. The proposed FTCLN provides scalable solution for intelligent botnet detection in large-scale IoT environments.
In light of rising cybersecurity threats, data center providers face growing pressure to protect their own management infrastructure from Distributed Denial-of-Service (DDoS) attacks. While tenant-managed cages generally fall outside the data center's direct security purview, a successful DDoS assault on core provider systems can indirectly disrupt network services. To address this availability assault, the authors developed a Graph Neural Network (GNN) based detection system which leverages Graph U-Nets to automatically classify and mitigate DDoS traffic. Although the model was developed using open-source network flows rather than proprietary data center logs, the model effectively identifies multi-layer DDoS attacks that resemble the malicious patterns threatening modern data centers. Adopting this system to data center environments requires minimal changes to existing operational workflows and processes. Specifically, the GNN based system can be integrated at critical areas within a data center's network infrastructure. Our model achieved an F1 score of over 95
The rapid growth of multimedia data generated by IoT devices, social platforms, and surveillance systems has created a strong demand for intelligent, secure, and real-time analytics. Conventional big data frameworks often suffer from high latency, centralized architectures, and inadequate integration of analytics and security. This paper proposes HPD-BDSE (Hybrid Parallel Distributed Big Data Search Engine), a distributed framework that integrates edge, fog, and cloud computing for efficient multimedia analytics, secure information retrieval, and knowledge discovery. In the proposed architecture, feature extraction is performed at edge nodes, while fog nodes handle distributed indexing and analytics, and cloud servers support global knowledge discovery. AI-driven models, searchable encryption, and federated learning are incorporated to enable privacy-preserving analytics and secure communication without significantly affecting system performance. Experimental results demonstrate a 46% reduction in latency, over threefold improvement in throughput compared with conventional big data frameworks, and only an 11% encryption overhead. The proposed framework provides a scalable, secure, and efficient solution for real-time multimedia processing and is well suited for applications in smart cities, healthcare, intelligent transportation, defence, and other large-scale distributed environments.
Photovoltaic technology has emerged as a leading renewable energy solution, converting sunlight into electricity through solar cells. Traditional manual inspection and rulebased algorithms struggle with scalability of defects in large photovoltaic datasets. Electroluminescent images often contain thin cracks and subtle anomalies, which are difficult to classify using conventional convolutional networks. To address these limitations, scale-aware dilated lightweight convolutional network (SADL-Net) was proposed for defect classification. The methodology integrates lightweight convolution, dilated convolution and scale-aware attention modules to emphasize defect-relevant features across multiple scales. Experiments were conducted using ELPV and PVEL-AD datasets, containing diverse photovoltaic defects with annotated ground truth bounding boxes. SADL-Net achieved. The proposed SADL-Net model achieved an accuracy of 97.23 % on the ELPV dataset and $\mathbf{9 5. 3 2 \%}$ on the PVEL-AD dataset. Overall, SADL-Net provides a balanced, effective, and statistically validated solution for solar panel defect classification applications globally.