The detection of a Denial of Service (DoS) attacks is a key challenge in network security, directly impacting the availability and reliability of networks. Such attacks have to be mitigated by implementing an accurate and timely detection mechanism to ensure the integrity of the network infrastructure. Driven by the shortcomings of conventional attack detection methods and the growing complexity of the network attacks, this work proposes a new customized Long Short-Term Memory (LSTM) model for DoS attacks detection. The proposed deep learning approach utilizes LSTM's strength in learning long-range dependencies in sequential data to model network traffic patterns over time. The effectiveness of the model is evaluated through comparative experiments. The primary outcome is that the proposed LSTM model has improved detection performance across all metrics of precision, recall, F1-score, and accuracy. The results demonstrate that the proposed LSTM architecture is a promising and trustworthy solution for enhancing intrusion detection systems (IDSs) and protecting network systems against DoS attacks.

This study performs an independent examination of the performance exhibited by NoSQL and SQL databases regarding key-value stores in parallel processing using a simulation model containing 15 nodes. Specifically, the focus is on comparing the efficiency of read, write, delete, and instantiate operations within the context of key-value stores implemented with both NoSQL (MongoDB, RavenDB, and Cassandra) and SQL (MS-SQL) databases within the average time of three runs. The results show that SQL achieved better read operation times, while NoSQL databases, especially RavenDB, had better results in the other operations.

Intrusion Detection and Prevention Systems (IDPSs) play a crucial role in safeguarding online connections against unauthorized access and malicious activities. To enable efficient and effective detection and mitigation, IDPSs must continuously improve their performance due to the constantly developing nature of cyber threats. However, an IDPS is more difficult to use and less reliable when it deals with huge amounts of data. This study aimed to improve the performance of IDPSs by employing optimization algorithms to reduce the data size. Particularly, the Harris Hawks Optimization (HHO) and Whale Optimization Algorithm (WOA) were combined for feature selection. The experimental results showed that the performance of the proposed IDPS was greatly improved by combining the HHO and WOA algorithms. Combining a Random Forest classifier with the suggested HHO/WOA feature selection method achieved very high results in accuracy (99.17%), recall (98.76%), precision (98.76%), and F1-score (98.43%).

The number of people and applications using the internet has increased substantially in recent years. The increased use of the internet has also resulted in various security issues. As the volume of data increases, cyber-attacks become increasingly sophisticated, exploiting vulnerabilities in network structures. The incorporation of modern technologies, particularly data mining, emerges as an essential method for analyzing huge amounts of data in real time, enabling the proactive detection of anomalies and potential security breaches. This research seeks to identify the most robust machine learning model for exploit detection. It applies five feature selection techniques and eight classification models to the UNSW-NB15 dataset. A comprehensive evaluation is conducted based on classification accuracy, computational efficiency, and execution time. The results demonstrate the efficiency of the Decision Tree model using Random Forest for feature selection in the real-time detection of exploit attacks, exhibiting an accuracy of 87.9%, along with a very short training (0.96 s) and testing time (0.29 ms/record).

As generative Artificial Intelligence (AI) models become increasingly integrated into software development workflows, understanding their efficiency and code quality is critical. This study offers a comprehensive comparison of three leading AI models—ChatGPT GPT-4-turbo, Claude Sonnet, and DeepSeek-V3—for automated code generation, focusing specifically on sorting algorithms. The models are evaluated across multiple metrics including execution time, memory usage, peak memory consumption, logical and physical file sizes, and code readability. Python implementations of Insertion Sort, Merge Sort, Quick Sort, and Heap Sort are generated by each model and benchmarked in a consistent Linux Docker environment. Results reveal that ChatGPT leads in overall efficiency, with the fastest average execution time, the lowest peak memory usage, and the highest readability scores. DeepSeek demonstrated competitive performance, especially in producing readable code, while Claude showed higher memory consumption and lower readability. This analysis provides practical insight into the trade-offs between code quality and system performance in AI-generated programming, offering valuable guidance for researchers and developers alike.