An intrusion detection system serves as the backbone for providing high-level network security. Different forms of network attacks have been discovered and they continue to become gradually more sophisticated and complicated. With the wide use of internet-based applications, cyber security has become an important research area. Despite the availability of many existing intrusion detection systems, intuitive cybersecurity systems are needed due to alarmingly increasing intrusion attacks. Furthermore, with new intrusion attacks, the efficacy of existing systems depletes unless they evolve. The lack of real datasets adds further difficulties to properly investigating this problem. This study proposes an intrusion detection approach for the modern network environment by considering the data from satellite and terrestrial networks. Incorporating machine learning models, the study proposes an ensemble model RFMLP that integrates random forest (RF) and multilayer perceptron (MLP) for increasing intrusion detection performance. For analyzing the efficiency of the proposed framework, three different datasets are used for experiments and validation, namely KDD-CUP 99, NSL-KDD, and STIN. In addition, performance comparison with state-of-the-art models is performed which suggests that the RFMLP can detect intrusion attacks with high accuracy than the existing approaches.

No abstract

During the COVID-19 pandemic, the spread of fake news became easy due to the wide use of social media platforms. Considering the problematic consequences of fake news, efforts have been made for the timely detection of fake news using machine learning and deep learning models. Such works focus on model optimization and feature engineering and the extraction part is under-explored area. Therefore, the primary objective of this study is to investigate the impact of features to obtain high performance. For this purpose, this study analyzes the impact of different subset feature selection techniques on the performance of models for fake news detection. Principal component analysis and Chi-square are investigated for feature selection using machine learning and pre-trained deep learning models. Additionally, the influence of different preprocessing steps is also analyzed regarding fake news detection. Results obtained from comprehensive experiments reveal that the extra tree classifier outperforms with a 0.9474 accuracy when trained on the combination of term frequency-inverse document frequency and bag of words features. Models tend to yield poor results if no preprocessing or partial processing is carried out. Convolutional neural network, long short term memory network, residual neural network (ResNet), and InceptionV3 show marginally lower performance than the extra tree classifier. Results reveal that using subset features also helps to achieve robustness for machine learning models.

No abstract

No abstract