Machine learning has recently become a popular algorithm in building reliable intrusion detection systems (IDSs). However, most of the models are static and trained using datasets containing all targeted intrusions. If new intrusions emerge, these trained models must be retrained using old and new datasets to classify all intrusions accurately. In real-world situations, new threats continuously appear. Therefore, machine learning algorithms used for IDSs should have the ability to learn incrementally when these new intrusions emerge. To solve this issue, we propose T-DFNN. T-DFNN is an algorithm capable of learning new intrusions incrementally as they emerge. A T-DFNN model is composed of multiple deep feedforward neural network (DFNN) models connected in a tree-like structure. We examined our proposed algorithm using CICIDS2017, an open and widely used network intrusion dataset covering benign traffic and the most common network intrusions. The experimental results showed that the T-DFNN algorithm can incrementally learn new intrusions and reduce the catastrophic forgetting effect. The macro average of the F1-score of the T-DFNN model was over 0.85 for every retraining process. In addition, our proposed T-DFNN model has some advantages in several aspects compared to other models. Compared to the DFNN and Hoeffding tree models trained with a dataset containing only the latest targeted intrusions, our proposed T-DFNN model has higher F1-scores. Moreover, our proposed T-DFNN model has significantly shorter training times than a DFNN model trained using a dataset containing all targeted intrusions. Even though several factors can affect the duration of the training process, the T-DFNN algorithm shows promising results in solving the problem of ever-evolving network intrusion variants.

Analisis Availabilitas dan Reliabilitas Multi-Master Database Server Dengan State Snapshot Transfers (SST) Jenis Rsync Pada MariaDB Galera Cluster

Implementasi Teknologi Virtualisasi Berbasis Kontainer untuk Perangkat Internet of Things pada Pertanian Presisi

The preparation of raw images for subsequent analysis, known as image preprocessing, is a crucial step that can boost the performance of an image classification model. Although deep learning has succeeded in image classification without handcrafted features, certain studies underscore the continued significance of image preprocessing for enhanced performance during the training process. Nonetheless, this task is often demanding and requires high-quality images to effectively train a classification model. The quality of training images, along with other factors, impacts the classification model’s performance and insufficient image quality can lead to suboptimal classification performance. On the other hand, achieving high-quality training images requires effective image preprocessing techniques. In this study, we perform exploratory experiments aimed at improving a classification model of unexposed potsherd cavities images via image preprocessing pipelines. These pipelines are evaluated on two distinct image sets: a laboratory-made, experimental image set that contains archaeological images with controlled lighting and background conditions, and a Jōmon–Yayoi image set that contains images of real-world potteries from the Jōmon period through the Yayoi period with varying conditions. The best accuracy performances obtained on the experimental images and the more challenging Jōmon–Yayoi images are 90.48% and 78.13%, respectively. The comprehensive analysis and experimentation conducted in this study demonstrate a noteworthy enhancement in performance metrics compared to the established baseline benchmark.

The Internet of Things (IoT) infrastructure exhibits numerous security vulnerabilities which have led to an increasing number of cyber-attacks. This problem has led to the development of Intrusion Detection Systems (IDSs) explicitly tailored for detecting cyber-attacks on IoT infrastructure, particularly IDSs that utilize machine learning models. To achieve high-performance machine learning models, the training data is pivotal. However, IoT infrastructure has limited computational resources, especially CPU, memory, and power. One solution is reducing the amount of data by selecting only certain features that have a significant impact on the quality of the machine learning models. This study proposes a novel hybrid framework to select the important features to build an efficient IDS model for IoT using the XGBoost algorithm. The performance of the proposed framework was rigorously tested using the network TON-IoT dataset, which is specifically designed to develop IDSs for IoT infrastructure. The experimental results show that our proposed framework yields machine-learning models with optimal performance while conserving computational resources. Through the implementation of our framework, we achieve a substantial reduction in features by 78.95%, coupled with a 3.18% Macro F1-score improvement. Furthermore, the framework also yields significant reductions in training, validation, and testing durations by 53.25%, 41.94%, and 47.06%, respectively. Also, it yields a model with impressive reductions in memory usage by 81.82%.