Despite the rapid evolution of Internet protocol-based messaging services, SMS still remains an indisputable communication service in our lives until today. For example, several businesses consider that text messages are more effective than e-mails. This is because 82% of SMSs are read within 5 min., but consumers only open one in four e-mails they receive. The importance of SMS for mobile phone users has attracted the attention of spammers. In fact, the volume of SMS spam has increased considerably in recent years with the emergence of new security threats, such as SMiShing. In this paper, we propose a hybrid deep learning model for detecting SMS spam messages. This detection model is based on the combination of two deep learning methods CNN and LSTM. It is intended to deal with mixed text messages that are written in Arabic or English. For the comparative evaluation, we also tested other well-known machine learning algorithms. The experimental results that we present in this paper show that our CNN-LSTM model outperforms the other algorithms. It achieved a very good accuracy of 98.37%.

Cybersecurity incidents have become a growing problem for the healthcare industry since the widespread introduction of technology into the healthcare systems. In recent years, the number of attacks has increased rapidly in healthcare, and it is now among the sectors most targeted by cyberattacks globally. These types of attacks are not only a threat to the data and finances of medical organizations, but they can also disrupt hospital operations and endanger the health and well-being of patients. Traditional security measures are not sufficient to protect the healthcare IT (Information Technology) environment due to its complexity and the heterogeneity of its medical devices. In this paper, we propose a new intrusion and malware detection system to secure the entire network of the healthcare system. The proposed solution includes two components: an intrusion detection system for medical devices installed in the healthcare network, and a malware detection system for data servers and medical staff computers. The objective is to secure the entire network independently of the installed devices and computers. The proposed system is based on an optimized LightGBM model and a Tranformer-based model. It is trained with four different datasets to guarantee a varied knowledge of the different types of attacks that can affect the healthcare sector. The used datasets have been generated from different environments undergoing IoT (Internet of Things), IoMT (Internet of Medical Things) and Windows malware attacks. The experimental evaluation of the approach showed remarkable accuracies of 99%.

Over the last decade, the Short Message Service (SMS) has become a primary communication channel. Nevertheless, its popularity has also given rise to the so-called SMS spam. These messages, i.e., spam, are annoying and potentially malicious by exposing SMS users to credential theft and data loss. To mitigate this persistent threat, we propose a new model for SMS spam detection based on pre-trained Transformers and Ensemble Learning. The proposed model uses a text embedding technique that builds on the recent advancements of the GPT-3 Transformer. This technique provides a high-quality representation that can improve detection results. In addition, we used an Ensemble Learning method where four machine learning models were grouped into one model that performed significantly better than its separate constituent parts. The experimental evaluation of the model was performed using the SMS Spam Collection Dataset. The obtained results showed a state-of-the-art performance that exceeded all previous works with an accuracy that reached 99.91%.

The Internet of Medical Things (IoMT) has significantly enhanced the healthcare sector by enabling advanced connectivity between smart medical devices, improving patient monitoring, and optimizing care quality. However, this increasing connectivity exposes these systems to cyberattacks that can compromise data confidentiality, disrupt device operations and endanger patient safety. Attacks on the IoMT, such as intrusions, ransomware, data tampering and denial-of-service, exploit vulnerabilities in medical devices, which often lack adequate security measures. Addressing these challenges requires robust attack detection solutions tailored to the constraints of IoMT environments. In this paper, we propose a novel approach based on Federated Learning (FL), enabling medical devices to collaboratively detect cyberattacks without directly sharing sensitive data. Unlike traditional FL systems that rely on computationally intensive neural networks, our approach leverages XGBoost—a lightweight yet powerful algorithm—to train detection models locally on devices. The XGBoost models are further optimized using a Bayesian method and integrated with an aggregation algorithm to construct an adaptive global model. We evaluate our approach using three IoMT datasets: CICIoMT2024, ECU-IoHT, and WUSTL-EHMS. Experimental results demonstrate that, in addition to minimizing the risk of medical data leakage, our method achieves superior detection accuracy compared to centralized approaches.

The dominance of Android in the global mobile market and the open development characteristics of this platform have resulted in a significant increase in malware. These malicious applications have become a serious concern to the security of Android systems. To address this problem, researchers have proposed several machine-learning models to detect and classify Android malware based on analyzing features extracted from Android samples. However, most existing studies have focused on the classification task and overlooked the feature selection process, which is crucial to reduce the training time and maintain or improve the classification results. The current paper proposes a new Android malware detection and classification approach that identifies the most important features to improve classification performance and reduce training time. The proposed approach consists of two main steps. First, a feature selection method based on the Attention mechanism is used to select the most important features. Then, an optimized Light Gradient Boosting Machine (LightGBM) classifier is applied to classify the Android samples and identify the malware. The feature selection method proposed in this paper is to integrate an Attention layer into a multilayer perceptron neural network. The role of the Attention layer is to compute the weighted values of each feature based on its importance for the classification process. Experimental evaluation of the approach has shown that combining the Attention-based technique with an optimized classification algorithm for Android malware detection has improved the accuracy from 98.64% to 98.71% while reducing the training time from 80 to 28 s.