The rapid advancement of autonomous driving technology has transformed modern transportation, offering enhanced safety, efficiency, and convenience. However, as these vehicles become increasingly connected and reliant on complex software and sensor-based systems, they also become prime targets for a wide range of cyber and privacy threats. This review paper comprehensively examines the current landscape of security and privacy in autonomous driving systems. We explore emerging attack vectors targeting key components such as sensor perception, vehicle-to-everything (V2X) communication, machine learning models, and internal control systems. Particular attention is given to adversarial machine learning, GPS spoofing, Controller Area Network (CAN) bus attacks, and data privacy breaches. In parallel, we evaluate existing defense mechanisms and mitigation strategies, including intrusion detection systems (IDS), secure communication protocols, hardware-based security modules, and privacy-preserving architectures. We also highlight key challenges in securing autonomous systems, identify gaps in current research, and propose directions for future work to build resilient and trustworthy autonomous vehicles. This review aims to provide researchers and practitioners with a consolidated foundation for understanding and advancing the security posture of next-generation autonomous driving technologies.

The Internet of Things (IoT) has expanded into a realm of cutting-edge integrated solutions across numerous applications, following three stages of development: communication, authentication, and computing. However, each layer inside the three tier IoT architecture faces a spectrum of security concerns due to the IoT’s openness, scope, and resource limits. Therefore, developing a secure IoT system is vital, shielding against attackers leveraging IoT devices to obtain network access and maintaining data security during transmission between these devices. Despite developments in Intrusion Detection Systems, identifying Denial-of-Service (DoS) and Distributed Denial-of-Service (DDoS) attacks in real-time remains a significant issue, especially in the environment of IoT devices, which are diverse and resource restricted. This study provides a Convolutional Neural Network-Support Vector Machine (CNN-SVM) hybrid technique, targeted at overcoming these limits by enhancing detection speed and accuracy, thus addressing this substantial gap in the area. This research offers a hybrid model that combines CNN for feature extraction with SVM as a classifier. This model employs a CNN to extract essential elements from the data and classifies attacks as either DDoS or benign. Our results highlight the potential performance of our model, which was trained on the real Canadian institute for cybersecurity (CIC) IoT dataset in 2023. Notably, our hybrid model outperformed classic machine learning (ML) alternatives such as CNN, SVM, K-nearest neighbors, Naïve Bayes, and Logistic Regression. During testing, our model attained a remarkable accuracy rate of 99% and an F 1-score of 99%, outperforming the highest-performing SVM ML model with an accuracy of 98% and the other ML methods.

Nowadays, technology is propagation rapidly that it is virtually completely replacing the real world with a “virtual world.” Electronic forensics important as medical forensics to investigate electronic crime” which increases with time”, to prevent unwanted file recovery, many computer users choose to overwrite files instead of deleting them to collect evidence and analysis by several methods and tools to present in front of the law. This paper studies the collection and analysis of files with an emphasis on deleted files from different resources and evaluates the performance of open-source programs for recovering deleted data using unconventional ways. It discusses some forensics tools, including FTK, and Encase, and the ability to extract the deleted file, showing a general comparison between forensics tools.

Breast cancer is a prevalent and serious disease that affects many women around the world every year. Detecting breast cancer early is crucial for improving survival rates and treating the illness effectively. Researchers are exploring various methods, including neural networks and machine learning, to assist in detecting the disease. However, due to limited data availability, leveraging pre-trained models trained on diverse image datasets has become a common practice. This article introduces a novel approach to identifying breast cancer that involves the utilization of a deep learning model utilizing the ResNet50 framework, coupled with heat mapping and gradient-weighted class activation mapping (Grad-CAM). The suggested method was primarily assessed using the FDDM dataset of Subtracted Contrast Enhanced Spectral Mammography (CDD-CESM) images. The outcomes from this model were then contrasted with those of five other well-known models: VGG16, VGG19, MobileNetV2, EfficientNet-B7, and standard ResNet50. The newly proposed model yielded an accuracy of 0.8920, which was better than the other models. Additionally, Grad-CAM showed nearly flawless feature extraction in a breast cancer classification assignment. In the discussion section, the suggested method was utilized with the MIAS dataset to ensure thoroughness and scalability, and to allow for comparison with prior research. The results demonstrated the effectiveness of the suggested approach, with an accuracy of 0.9830 achieved on the MIAS dataset, surpassing previous works. This study significantly enhances the improvement of breast cancer detection through the integration of deep learning, the ResNet50 architecture, and visualization methods including heat maps and Grad-CAM.

The escalating sophistication of cyber threats requires transparent and reproducible benchmarks for intelligent security paradigms. This study presents a comprehensive benchmark analysis of a machine learning pipeline for network intrusion detection, addressing critical deployment oriented challenges such as class imbalance, feature optimization, and cross-environment generalization. Trained rigorously on the NF-CSE-CIC-IDS2018-v2 dataset and validated on the distinct UNSWNB15 dataset, this work tackles the complexities of identifying diverse network threats through the systematic integration of data preprocessing, advanced class-imbalance handling with SMOTE, and an embedded feature selection methodology. A comparative evaluation is conducted between state-of-the-art ensemble models (Random Forest and XGBoost), recent deep learning approaches, and a logistic regression baseline, examining predictive accuracy, computational trade-offs, and per-class performance across stealthy and volumetric attack types. The optimized Random Forest model achieves 99.95% accuracy and a 0.9837 F1-score on the primary dataset, while demonstrating strong generalization performance with a 94.8% F1-score on cross-validation, supported by thorough overfitting analysis and model validation procedures.

Wireless sensor networks (WSN) have become widely used as technology in various industries, including the military, healthcare, and automation. regardless of their usefulness, WSNs are vulnerable to various cyber threats, such as denial of service (DoS), node replication attacks, and physical tempering. Due to the nature of WSNs being resource-constrained, Traditional IDS frequently fail to address these challenges, which leads to an increase in false alarm rates and limited accuracy in detection. This paper presents a new intrusion detection approach leveraging the Parrot Optimizer (PO) algorithm. The PO algorithm integrated the four major behavioral strategies to dynamically optimize IDS formation. The suggested IDS aims to improve computing efficiency, decrease false alarm rates, and increase detection accuracy by utilizing these flexible techniques, addressing the challenges of WSNs. The achieved results show that the implementation of bio-inspired algorithms enhances the performance of the IDS by improving the accuracy of detecting threats targeting the WSNs networks.