The increasing sophistication of cyber threats necessitates the development of advanced security mechanisms to protect modern networks. Among these threats, spoofing attacks pose a significant risk by enabling malicious actors to impersonate legitimate entities. To address this challenge, we propose a novel Transformer-based deep learning framework designed for the effective detection of spoofing attacks. The core of our novel model is a Transformer neural network, enhanced with a custom attention mechanism to improve feature extraction and classification accuracy. To enhance model interpretability and foster trust in AI-driven security systems, we integrate Explainable AI (XAI) techniques, specifically SHAP analysis, allowing for a deeper understanding of feature contributions in decision-making. The proposed model utilized the CIC IoMT2024 dataset, a benchmark with limited prior research on spoofing attack detection. Further, our approach incorporates comprehensive data preprocessing techniques and employs over-sampling using the synthetic minority oversampling technique (smote) and cleaning using (tomek) these techniques are integrated into links smotetomek to mitigate class imbalance, ensuring a more representative training dataset. The proposed framework is evaluated using benchmark dataset datasets, demonstrating high binary classification performance in spoofing attacks through key metrics such as accuracy, confusion matrix analysis, and other classification benchmarks. The proposed model archived an exact result with Accuracy 99.71%. The findings highlight the potential of Transformer-based architectures in cybersecurity applications, paving the way for real-time threat detection and adaptive defense mechanisms.

Ultrasound imaging plays an important role in fetal growth and maternal-fetal health evaluation, but due to the complicated anatomy of the fetus and image quality fluctuation, its interpretation is quite challenging. Although deep learning include Convolution Neural Networks (CNNs) have been promising, they have largely been limited to one task or the other, such as the segmentation or detection of fetal structures, thus lacking an integrated solution that accounts for the intricate interplay between anatomical structures. To overcome these limitations, Fetal-Net-a new deep learning architecture that integrates Multi-Scale-CNNs and transformer layers-was developed. The model was trained on a large, expertly annotated set of more than 12,000 ultrasound images across different anatomical planes for effective identification of fetal structures and anomaly detection. Fetal-Net achieved excellent performance in anomaly detection, with precision (96.5%), accuracy (97.5%), and recall (97.8%) showed robustness factor against various imaging settings, making it a potent means of augmenting prenatal care through refined ultrasound image interpretation.

Advanced CNN-based multi-stage deep learning method for superior knee joint diagnostics with enhanced accuracy, precision, and recall in medical imaging.

The proposed CapsNet Model excels in capturing spatial dependencies and hierarchical feature relationships, surpassing the capabilities of traditional convolutional architectures.

The Internet of Medical Things (IoMT) has transformed healthcare delivery through real-time monitoring and data exchange. However, this integration of smart medical devices has also introduced critical cybersecurity threats, particularly spoofing attacks, which can compromise patient safety and system reliability. Conventional Intrusion Detection Systems (IDS) often fail to address IoMT-specific challenges such as class imbalance, computational constraints, and the need for real-time adaptability. This study proposes a Capsule Network (CapsNet)-based IDS that leverages spatial dependency modeling and hierarchical feature relationships to detect spoofing attacks in IoMT environments. Using the CICIoMT2024 dataset, we implemented a binary classification framework where spoofing instances were labeled as abnormal (1) and normal behavior as (0). The model architecture integrates a convolutional feature extractor, dynamic routing by agreement, dropout regularization, dense refinement layers, Binary Cross-Entropy loss, and the Adam optimizer. Class imbalance was addressed through synthetic oversampling and data augmentation using Generative Adversarial Networks (GANs). Experimental evaluation achieved 99.83% accuracy, 99.98% precision, 99.985% recall, and a 98.99% F1-score, outperforming CNN, LSTM, and hybrid CNN-LSTM baselines on the same dataset. Statistical validation with 10-fold cross-validation yielded consistent performance (±0.05% standard deviation). The proposed CapsNet-based IDS demonstrates high detection performance and robustness, making it suitable for deployment in resource-constrained IoMT environments. Future work will extend the framework to multiclass spoofing detection, real-time adaptation, and adversarial robustness testing.

Ultrasound imaging plays an important role in fetal growth and maternal-fetal health evaluation, but due to the complicated anatomy of the fetus and image quality fluctuation, its interpretation is quite challenging. Although deep learning include Convolution Neural Networks (CNNs) have been promising, they have largely been limited to one task or the other, such as the segmentation or detection of fetal structures, thus lacking an integrated solution that accounts for the intricate interplay between anatomical structures. To overcome these limitations, Fetal-Net-a new deep learning architecture that integrates Multi-Scale-CNNs and transformer layers-was developed. The model was trained on a large, expertly annotated set of more than 12,000 ultrasound images across different anatomical planes for effective identification of fetal structures and anomaly detection. Fetal-Net, with excellent precision (96.5%), accuracy (97.5%), and recall (97.8%) showed robustness factor against various imaging settings, making it a potent means of augmenting prenatal care through refined ultrasound image interpretation.