1 January 2026 in IEEE Access
The rapid evolution of malicious software continues to challenge modern cybersecurity systems, driven by increasingly sophisticated evasion techniques such as polymorphism, packing, and code obfuscation. While machine learning has proven effective in detecting previously unseen malware, its practical adoption is often constrained by high-dimensional feature spaces and the complexity of model and hyperparameter selection. This paper presents an evolutionary AutoML-based framework that integrates Genetic Algorithm (GA) feature selection with Automated Machine Learning (AutoML) optimization for feature-efficient malware detection. The proposed approach employs a GA-driven search to identify a compact and informative subset of features from the high-dimensional EMBER dataset, effectively eliminating redundant attributes while preserving discriminative capability. The resulting reduced feature representation is then utilized by an AutoML pipeline to automatically discover an optimized classification model and hyperparameter configuration. Experimental results demonstrate that the proposed framework reduces the original feature space from 2381 to approximately 400 features while maintaining strong predictive performance. The optimized GA + AutoML pipeline achieves an accuracy of 96.9% with an ROC-AUC approaching 0.99. Although marginally lower than full-feature baselines, the performance remains competitive given the substantial reduction in dimensionality. Furthermore, ablation analysis confirms that the combination of evolutionary feature selection and automated model optimization provides complementary benefits, offering a robust trade-off between accuracy and efficiency. These findings highlight the effectiveness of the proposed framework in achieving a strong balance between predictive performance and feature-space reduction under benchmark conditions. However, further evaluation under temporal and cross-domain settings is required to fully assess real-world generalization.
22 July 2026 in Journal of Cyber Security Technology
1. Android is the world's most widely used mobile operating system because it is open source and offers a large number of third-party applications. However, the popularity of the platform has also ...
9 July 2026 in VFAST Transactions on Software Engineering
As web applications continue to become more and more complex, they have become opportunistic for different types of security threats. These threats are usually represented by various attack types and for every attack it is necessary to choose the proper method and approaches to discover it. However, the lack of a structured approach to analyzing the relationships between security threats, attack types, and testing techniques hinders the development of efficient security strategies. By leveraging DBSCAN, this study groups similar security incidents to identify hidden relationships and trends that can inform more targeted security measures. The methodology entails gathering information from the latest high-quality research on web application security, clustering the security threats by employing DBSCAN algorithm, and then comparing the generated clusters to attack types, as well as with the various testing techniques. This analysis provides valuable insights into how different attack types are associated with specific security threats, and which testing techniques are most effective for detecting and mitigating these threats. The findings contribute towards a more structured approach to web application security, offering recommendations for improved threat detection and prevention strategies.