A revolution in network technology has been ushered in by software defined networking (SDN), which makes it possible to control the network from a central location and provides an overview of the network’s security. Despite this, SDN has a single point of failure that increases the risk of potential threats. Network intrusion detection systems (NIDS) prevent intrusions into a network and preserve the network’s integrity, availability, and confidentiality. Much work has been done on NIDS but there are still improvements needed in reducing false alarms and increasing threat detection accuracy. Recently advanced approaches such as deep learning (DL) and machine learning (ML) have been implemented in SDN-based NIDS to overcome the security issues within a network. In the first part of this survey paper, we offer an introduction to the NIDS theory, as well as recent research that has been conducted on the topic. After that, we conduct a thorough analysis of the most recent ML- and DL-based NIDS approaches to ensure reliable identification of potential security risks. Finally, we focus on the opportunities and difficulties that lie ahead for future research on SDN-based ML and DL for NIDS.

The integrity and security of data must be protected in the framework of the Internet of Things (IoT). This article addresses the difficulties presented by possible cyber threats to IoT devices by introducing a unique feature selection technique called Pearson correlation matrix with random forest (PCM‐RF). IoT device security is greatly influenced by machine learning techniques, which mostly depend on the caliber of characteristics taken from IoT datasets. By merging the advantages of RF with PCM, PCM‐RF maximizes feature selection and fine‐tunes features to improve the efficacy of current machine learning techniques and bolster classification algorithms' detecting powers. The study focuses on addressing limitations in existing ways of training and testing classification algorithms, which frequently lack strategies for optimizing and fine‐tuning features. Thirty‐four different forms of network assaults are included in the IoTCIC2023 dataset, used to assess PCM‐RF. Results demonstrate PCM‐RF's effectiveness, with XGBoost achieving an astounding accuracy of 99.39% and an 86% detection rate. Comparative studies highlight PCM‐RF's superiority in detection and classification results, offering insights into IoT security and emphasizing its potential to improve the overall device robustness in the IoT ecosystem.

To combat the growing danger of zero-day attacks on IoT networks, this study introduces a Cluster-Based Classification (CBC) method. Security vulnerabilities have become more apparent with the growth of IoT devices, calling for new approaches to identify unique threats quickly. The hybrid CBC approach uses optimized k-means clustering to find commonalities across different abnormalities, intending to quickly identify and classify unknown harmful attacks in a varied IoT network. The technique is fine-tuned for eight-class and two-class classifications, supporting different attacks using the IoTCIC2023 dataset and SelectKBest feature selection. Robust analysis is achieved by evaluating and aggregating the performance of machine learning classifiers such as XGBoost, AdaBoost, KNN, and Random Forest. In two-class classification, Random Forest achieves 95.11% accuracy, while in eight-class classification, KNN tops the charts with 88.24%. These results demonstrate noteworthy accuracy. The suggested CBC technique is effective, as shown by comparisons with state-of-the-art approaches. Despite several caveats and dataset specifications, this study provides a useful tool for academics and practitioners in the ever-changing field of cybersecurity by suggesting a method to strengthen the security of IoT networks against new threats.

Automated silicon wafer defect inspection is critical for sustaining yield and reliability in semiconductor manufacturing. Traditional image processing and feature engineering approaches struggle with complex and evolving defect patterns, while deep learning methods, although effective, increase computational cost and risk of overfitting. Many existing models address class imbalance through synthetic data, which can introduce artifacts and misrepresent the actual defect distributions. Additionally, conventional convolutional neural networks remain limited in capturing global context, leading to the misclassification of visually similar defects. This study addresses these issues through a simple yet effective two-stage approach. The proposed ensemble attention convolutional neural network (EACNN) first performs binary defect detection to distinguish between defective and non-defective samples, followed by a dedicated defect-type classification for fine-grained categorization. This staged design decomposes the complex multi-class problem into manageable subtasks and mitigates class dominance without synthetic data. The model further incorporates spatial and channel attention mechanisms to strengthen discriminative feature learning and improve the representation of salient defect regions. Focal loss is employed to mitigate class imbalance by down-weighting easily classified examples and placing greater emphasis on hard, misclassified samples. Optimization strategies, including batch normalization, dropout, and global average pooling, are adopted to improve generalization, reduce parameter complexity, and accelerate convergence. Experiments on the WM-811K dataset through 10-fold cross-validation demonstrated the effectiveness of EACNN and achieved 95.57% accuracy, 93.67% precision, 95.41% recall, 98.76% specificity, 94.47% F-measure, and 94.51% G-Mean. Comparisons with classical, attention-based, and imbalance-handling methods confirmed the superior performance of EACNN. The results underscore EACNN’s ability to learn highly discriminative features while preserving the integrity of real defect distributions.