Transactions on Emerging Telecommunications Technologies最新文献

In today's digital world, with increasing threats of cyberattacks and unauthorized data access, protecting confidential information demands more robust security mechanisms. Cryptography and steganography are two prominent techniques employed to secure data. However, conventional steganography suffers from reduced embedding capacity and the risk of image distortion. To overcome these challenges, this research proposes a novel hybrid framework to enhance data security and embedding efficiency. The approach comprises two phases including the embedding phase and the extraction phase. In the embedding phase, both the cover and secret images undergo a 3-level discrete wavelet transform (DWT) using the Daubechies wavelet. Region selection in the transformed cover image is optimized by extracting and leveraging various features, including color, shape, deep features, and local Gabor transitional pattern (LGTrP) features. These features are processed via a modified Bidirectional Long Short-Term Memory (Bi-LSTM) model, enhanced with architectural improvements, which boost feature learning. Simultaneously, the secret image undergoes transformation using a modified Arnold map integrated with a Bernoulli map allows faster execution. The modified Arnold function's outcome is subjected to an encryption process. The embedding process is done after the encryption process; the modified Blowfish algorithm is used for the decryption process. Subsequently, the inverse Bernoulli map is utilized, with the resultant output given to the inverse Arnold map. Finally, an inverse 3-level DWT reconstructs the original secret image. Comparative evaluations demonstrate the proposed framework attains lower KPA and KCA rates of 0.12 and 0.15, respectively, which underscores the innovation of integrating a steganography-cryptography model in securing sensitive data against sophisticated attacks.

Healthcare data holds immense potential to improve diagnostics and treatment, but centralized collection risks patient privacy and suffers from limited labeled samples. Existing methods fall short in securely leveraging distributed data while reducing annotation costs. To address this, we propose FTAL-QNC—a novel Federated Transfer Active Learning framework with Quantized Neural Cryptography—that enables privacy-preserving, communication-efficient, and label-efficient collaborative model training. FTAL-QNC integrates four core components in a unified architecture: (1) Federated learning for decentralized model training without data sharing, (2) Transfer learning to handle data heterogeneity across hospitals, (3) Active learning to minimize manual labeling by prioritizing informative samples, and (4) Quantized neural cryptography to ensure secure, low-overhead exchange of encrypted model updates. Empirical evaluations on real-world datasets, including Lung CT and ChestX-ray14, demonstrate that FTAL-QNC enhances segmentation and classification accuracy to 97.3% and 97.0% recall for Lung CT, respectively, while significantly reducing annotation effort compared to standard federated learning and other sampling methods. Our contributions include a privacy-preserving and communication-efficient collaborative framework, an integrated active learning mechanism for efficient data labeling, and a secure aggregation protocol via quantized neural cryptography. These results demonstrate FTAL-QNC's potential to advance safe, collaborative medical research and improve patient outcomes.

The rapid expansion of digitalization has intensified cybersecurity risks, exposing critical network vulnerabilities despite significant advances in encryption and intrusion detection systems (IDS). Many existing deep learning–based IDS still struggle with high false-positive rates, misclassification, and limited adaptability, reducing their effectiveness in real-time defense scenarios. To address these limitations, this study proposes a Polymorphic Graph Gudermannian Neural Network integrated with Adaptive Chaotic Satin Bowerbird Optimization (PG-GNN-AC-SBO), complemented by a lightweight encryption mechanism. The framework incorporates a Fuzzy K-Top Matching Value (FKTMV) module for robust preprocessing and normalization, along with a Hybrid Cat Hunting Sea-Horse Optimizer (H-CHO-SHO) for efficient and interpretable feature selection. The PG-GNN classifier employs graph-based learning and a Gudermannian nonlinear activation function to effectively capture complex traffic behavior, while AC-SBO dynamically tunes hyperparameters to enhance stability and classification accuracy. To ensure data confidentiality, a Synchronously Scrambled Diffuse Encryption (SSDE) scheme is applied, delivering strong security with low computational overhead. Experimental evaluations on the NSL-KDD and CICIDS2017 datasets demonstrate the superiority of the proposed approach, achieving up to 99.82% accuracy and outperforming state-of-the-art methods. The encryption and decryption times of 3.50 and 3.55 ms further confirm the model's lightweight design. Overall, the proposed system provides high throughput with minimal latency, demonstrating strong potential for real-time and large-scale cybersecurity deployments.

The rise in network intrusions has led to significant consequences, including privacy violations, financial losses, and unauthorized data transfers. Attackers exploit vulnerabilities in network systems, compromising security and disrupting services. Traditional intrusion detection systems (IDS) often face challenges such as false positives, delayed threat identification, and poor detection of minority attack classes. To address these issues, this research proposes advanced deep reinforcement learning with deep learning-based NIDS for improved threat detection and mitigation. Data from IoT-2023, BoT-IoT, CIC-IoT 2023, and RT-IoT 2022 datasets are preprocessed through null value handling, data cleaning, one-hot encoding, and Min-Max normalization. To enhance the detection of minority attacks, the Tabular Auxiliary Classifier Generative Adversarial Network (TACGAN) is employed for synthetic data augmentation. Feature extraction is performed using the Graph Sample and Aggregate Attention Network (GSAAN), which captures basic, content, and traffic-based features. Significant features are selected using the Mountaineering Team-Based Optimization (MTBO). Attack classification is carried out using a novel ensemble of the Improved Double Deep Q-Network (IDDQN) and Deep Autoregression Feature Augmented Bidirectional LSTM (DAF-BiLSTM), which is termed the OptIDQDBiLSTM approach, ensuring robust learning of spatial and temporal dependencies. Hyperparameter tuning is optimized using the Boosted Wild Horse Optimization Algorithm (BWHOA). Experimental results show that the proposed approach outperforms existing IDS methods, achieving higher detection rates, improved accuracy, and a reduced false alarm rate while maintaining computational efficiency. While comparing with existing state of the art approaches, the proposed approach surpasses existing methods with over 99.64% accuracy, 99.34% precision, and 99.42% recall. These findings demonstrate the effectiveness of deep reinforcement learning in enhancing network security against evolving cyber threats.

The Internet of Things (IoT) is particularly vulnerable in this new era, as IoT devices often rely on lightweight encryption and security measures due to their limited processing capabilities and power constraints. Existing signature-based intrusion detection strategies are inadequate against the advanced and adaptive nature of quantum attacks, which can exploit the polymorphic and metamorphic behavior of quantum-enhanced malware. This research addresses the challenges posed by a possible attack scenario named the “Quantum-Enhanced Cloak Malware (QECM) Attack” and aims to provide enhanced protection to IoT systems against this sophisticated threat. The proposed “Intelligent Swift Scan Quantum-Resilient Intrusion Detection System (ISS-QR-IDS)” integrates advanced techniques to enhance detection speed and accuracy, mitigate risks associated with polymorphic and metamorphic malware behaviors, and secure communication channels against quantum threats. The model incorporates the Parallel Vario-Isolation Detector, which combines Variational Autoencoders (VAEs) and Parallelized Isolation Forests to detect quantum-enhanced malware, and Hypergraph Attention Networks (HGA-Net), leveraging Hypergraph Neural Networks (HGNNs) and Graph Attention Networks (GATs) to detect the critical interactions and improve anomaly detection accuracy. Additionally, postquantum cryptographic algorithms like NTRU Encrypt and FALCON ensure secure communication channels and data integrity. By combining these advanced techniques, ISS-QR-IDS aims to provide a robust defense mechanism against sophisticated cyber threats targeting IoT networks, ensuring their security and resilience in the face of quantum computing advancements.

To address the challenges of false negatives and false positives of small objects and the difficulty of fine-grained behavior recognition in complex traffic scenarios, this paper constructs a hybrid deep learning framework based on image detection to synergistically improve multi-object localization accuracy and semantic understanding capabilities. The framework first uses a combination of Gaussian and bilateral filtering for denoising, enhancing input quality and improving detection sensitivity for small objects. In the detection phase, the YOLOv5s (You Only Look Once 5s) model is used as the baseline. The Convolutional Block Attention Module (CBAM) attention mechanism is applied to enhance the representation of key features. K-means clustering is used to adaptively generate prior anchor boxes that match the scale distribution of objects in traffic scenarios. The CIoU (Complete Intersection over Union) loss function is also used to optimize bounding box regression accuracy, improving small object detection performance while maintaining model lightweight. To achieve fine-grained semantic understanding, a two-branch classification network is designed. The attribute branch uses the ConvNeXt-Tiny (Convolutional Next-Generation Tiny) structure to extract static appearance features, while the event branch utilizes the nonlocal operations module to capture dynamic contextual dependencies. Weighted fusion of these two features enables joint recognition of attributes and behaviors. A GNN-CNN (Graph Neural Network-Convolutional Neural Network) hybrid classification module is also constructed. The GNN models the spatiotemporal interactions between vehicles, while a lightweight CNN extracts local texture features. These features are adaptively fused using the Squeeze-and-Excitation (SE) attention mechanism, and a softmax classifier performs traffic behavior judgment. Experiments show that the YOLOv5s-CBAM model achieves a mean average precision (mAP) of 0.55 for detecting extremely small objects (< 16 × 16). In the overloaded vehicle detection task, the GNN-CNN module achieves accuracy and recall of 0.92 and 0.90, respectively. This hybrid deep learning framework provides reliable technical support for automated traffic inspections. It improves the accuracy and stability of small object detection and fine-grained event recognition in complex traffic scenarios. Its modular design and strong scalability make it widely applicable and conducive to promoting intelligent transportation towards higher levels of automation.

In recent years, cloud computing has gained enormous development in computing systems. The cloud computing environment provides diverse benefits to its cloud users via the internet including storage, applications, on-demand services, etc. Nowadays, it has been accepted and utilized by various companies for uploading their massive amounts of data to a cloud platform. As a result, various cloud computing-based IDS (CIDS) techniques are developed to prevent a cloud network from attacks and protect the data from internal and external anomalous activities. Despite that, security and privacy concerns remain a significant challenge, which demands an effective methodology to ensure user confidentiality and integrity. Thus, we proposed a Stacked Convolutional and Recurrent Contractive Sparse Autoencoder (SCRCS-AE) and Levy flight and reconstructed mathematical optimization acceleration-based Arithmetic Optimization Algorithm (LRMOA-AOA) for an efficient ID in a cloud environment. In this paper, we stack three SCRCS-AE blocks to extract their features. A single SCRCS-AE block involves a convolutional encoder and recurrent decoder to capture long-term dependencies and rebuild input in forward and reverse directions for excellent feature extraction and classification of different intrusions. The integration of sparse and contractive loss is deployed to extract high-dimensional data features to boost the SCRCS-AE model's generalizability and robustness. The LRMOA-AOA optimization algorithm integrates a Levy flight distribution and arithmetic optimization algorithm (AOA) approach that tunes the hyperparameters to enhance the efficacy of the SCRCS-AE. The proposed SCRCS-AE achieved 98.73% accuracy, 98.46% detection rate, 1.27% false alarm rate, and 98.61% precision on the UNSW-NB15 dataset and attained 97.93% accuracy, 97.74% detection rate, 2.07% false alarm rate, and 97.59% precision on the NSL-KDD dataset. These superior outcomes show that the proposed SCRCS-AE technique works well on CIDS in detecting diverse assaults with higher detection rates and lower false alarm rates to strengthen cloud network security and privacy.

The Internet of Vehicles (IoV) collects real-time data on traffic, environmental conditions, and vehicle behavior through vehicle interconnection and interaction with infrastructure, providing support for the of Machine Learning (ML) in intelligent decision-making. However, centralized learning approaches suffer from issues like privacy leakage and high communication costs. Federated Learning (FL) addresses these issues by sharing local model updates, but in IoV environments, challenges such as data heterogeneity result in slow convergence, limited communication resources, and security threats like gradient leakage. To tackle these challenges, this paper proposes Adaptive Blockchain-based Hierarchical Federated Learning with Gradient Alignment (ABHFL). ABHFL groups vehicle nodes and RSUs into a hierarchical structure to perform local training, gradient alignment, and model aggregation at different levels. The proposed Adaptive Gradient Alignment (AGA) mechanism aligns the update directions of nodes towards the global optimal direction through multiple rounds of alignment after local gradient computation, accelerating model convergence and ensuring that the gradients uploaded contribute positively to global optimization. In addition, a lightweight Proof-of-Gradient-Alignment (PoGA) consensus mechanism is designed, which performs two-stage verification of the uploaded gradients and integrates reputation scores and blockchain storage to guarantee gradient reliability and protect against attacks. Extensive experiments demonstrate that ABHFL significantly improves model convergence, communication efficiency, and security reliability, providing an effective and robust solution for FL in IoV scenarios.

In general, multi-user multiple input multiple output orthogonal frequency division multiplexing (MU-MIMO-OFDM) allows multiple users to interconnect to a base station simultaneously using OFDM modulation and various antennas. However, managing resources like energy and minimizing delays is difficult, requiring smart solutions for smooth operation and better performance. Thus, a joint power and delay optimization based resource allocation using Enhanced Elman Spiking Sparse Graph Networks (EESS-Gnet) with Humboldt Squid Optimization Algorithm (HSOA) and Reuse-Based Online Joint Routing Scheduling Optimization (ROJR) (EESS-GNet-HSOA-ROJR) in MU-MIMO-OFDM system is proposed in this manuscript. The proposed mechanism is performed in two stages that are power allocation and delay optimization. The goal of the first phase is to maximize throughput by allocating network resources to user equipments (UEs) based on transmission rate and power through an EESS-Gnet. In order to reduce the loss function, HSOA is proposed to optimize the layers of EESS-Gnet. In the second stage, ROJR is proposed for optimizing delay in the MU-MIMO-OFDM system. In the ROJR approach, the delay bound value is estimated by scheduling the transmission flows in the channel. The simulations of EESS-GNet-HSOA-ROJR were conducted using MATLAB software. The suggested resource allocation algorithm's performance is assessed and contrasted with the current method of measuring different QoS metrics, including throughput, delay, fairness index, power consumption, spectrum capacity, and loss rate. Thus, the proposed approach has attained 26.46%, 23.09%, and 21.98% higher throughput, 29.78%, 26.86%, and 20.25% improved energy efficiency, 17.45%, 15.98%, and 14.02% lower processing time, and 27.89%, 34.87%, and 23.56% lower loss rate than other conventional approaches like PDO-URA, PCO-OBT, and ADNN-ALSTM-TRDA methods respectively.