In recent years, many methods for intrusion detection systems (IDS) have been designed and developed in the research community, which have achieved a perfect detection rate using IDS datasets. Deep neural networks (DNNs) are representative examples applied widely in IDS. However, DNN models are becoming increasingly complex in model architectures with high resource computing in hardware requirements. In addition, it is difficult for humans to obtain explanations behind the decisions made by these DNN models using large IoT-based IDS datasets. Many proposed IDS methods have not been applied in practical deployments, because of the lack of explanation given to cybersecurity experts, to support them in terms of optimizing their decisions according to the judgments of the IDS models. This paper aims to enhance the attack detection performance of IDS with big IoT-based IDS datasets as well as provide explanations of machine learning (ML) model predictions. The proposed ML-based IDS method is based on the ensemble trees approach, including decision tree (DT) and random forest (RF) classifiers which do not require high computing resources for training models. In addition, two big datasets are used for the experimental evaluation of the proposed method, NF-BoT-IoT-v2, and NF-ToN-IoT-v2 (new versions of the original BoT-IoT and ToN-IoT datasets), through the feature set of the net flow meter. In addition, the IoTDS20 dataset is used for experiments. Furthermore, the SHapley additive exPlanations (SHAP) is applied to the eXplainable AI (XAI) methodology to explain and interpret the classification decisions of DT and RF models; this is not only effective in interpreting the final decision of the ensemble tree approach but also supports cybersecurity experts in quickly optimizing and evaluating the correctness of their judgments based on the explanations of the results.

Non-Intrusive Load Monitoring (NILM) systems have gained popularity in recent years for saving more energy. To reduce sensing infrastructure costs, NILM monitors the electrical loads based on a machine learning method. We propose a novel approach to improve the performance of classifying household appliances at a high sampling rate called FFT-BDT. The proposed method includes two main processes. The first process is generating novel features in the feature extraction stage. These features are the magnitude and phase (MP) at lower odd-numbered harmonics based on the Fast Fourier Transform (FFT). MP features are steady-state features at high frequency and used as input for a learning model. The second process is where a machine learning model, a bagging decision tree (BDT), learns the novel MP features. The proposed method enhances the accuracy of recognizing different appliances that have similar power consumption. To evaluate the FFT-BDT, we experimented on two NILM datasets, including the public PLAID dataset and our own private dataset. The method outperformed prior methods and could significantly contribute to load identification in NILM.

In recent years, numerous explainable artificial intelligence (XAI) use cases have been developed, to solve numerous real problems in industrial applications while maintaining the explainability level of the used artificial intelligence (AI) models to judge their quality and potentially hold the models accountable if they become corrupted. Therefore, understanding the state-of-the-art methods, pointing out recent issues, and deriving future directions are important to drive XAI research efficiently. This paper presents a systematic literature review of local explanation techniques and their practical applications in various industrial sectors. We first establish the need for XAI in response to opaque AI models and survey different local explanation methods for industrial AI applications. The number of studies is then examined with several factors, including industry sectors, AI models, data types, and XAI-based usage and purpose. We also look at the advantages and disadvantages of local explanation methods and how well they work in practical settings. The difficulties of using local explanation techniques are also covered, including computing complexity and the trade-off between precision and interpretability. Our findings demonstrate that local explanation techniques can boost industrial AI models’ transparency and interpretability and give insightful information about them. The efficiency of these procedures must be improved, and ethical concerns about their application must be resolved. This paper contributes to the increasing knowledge of local explanation strategies and offers guidance to academics and industry professionals who want to use these methods in practical settings.

Numerical simulation of fluids is important in modeling a variety of physical phenomena, such as weather, climate, aerodynamics, and plasma physics. The Navier–Stokes equations are commonly used to describe fluids, but solving them at a large scale can be computationally expensive, particularly when it comes to resolving small spatiotemporal features. This trade-off between accuracy and tractability can be challenging. In this paper, we propose a novel artificial intelligence-based method for improving fluid flow approximations in computational fluid dynamics (CFD) using deep learning (DL). Our method, called CFDformer, is a surrogate model that can handle both local and global features of CFD input data. It is also able to adjust boundary conditions and incorporate additional flow conditions, such as velocity and pressure. Importantly, CFDformer performs well under different velocities and pressures outside of the flows it was trained on. Through comprehensive experiments and comparisons, we demonstrate that CFDformer outperforms other baseline DL models, including U-shaped convolutional neural network (U-Net) and TransUNet models.

Credit card fraud detection remains a significant challenge in the financial industry, necessitating advanced models to identify fraudulent activities while minimizing false positives accurately. Traditional machine learning approaches, such as Multilayer Perceptrons (MLP), have been widely used but often struggle with interpretability and parameter optimization issues. Kolmogorov-Arnold Networks (KAN) present a promising alternative by addressing these limitations through their inherent structure, which allows for more interpretable and potentially more accurate models. This paper explores the application of KAN in the context of credit card fraud detection, motivated by the need for more effective and interpretable solutions. We implement and evaluate three MLP, KAN, and efficient KAN models using two publicly available credit card fraud datasets. Our experimental results demonstrate that both KAN and efficient KAN significantly outperform the traditional MLP model in terms of detection accuracy while reducing the number of parameters compared to MLP. The findings underscore the potential of KAN and its efficient variant as superior alternatives for credit card fraud detection, offering enhanced accuracy and interpretability. This study provides valuable insights into model performance and parameter efficiency, guiding future research and practical applications in fraud detection systems.

In recent years, adversarial attack methods have been deceived rather easily on deep neural networks (DNNs). In practice, adversarial patches cause misclassification that can be extremely effective. However, many existing adversarial patches are used for attacking DNNs, and only a few of them apply to both the DNN and its explanation model. In this paper, we present different adversarial patches that misguide the prediction of DNN models and change the cause of prediction results of interpretation models, such as gradient-weighted class activation mapping. The proposed adversarial patches have appropriate location and perturbation ratios, which comprise visible or less visible adversarial patches. In addition, image patches within small arrays are localized without covering or overlapping with any of the main objects in a natural image. In particular, we generate two adversarial patches that cover only 3% and 1.5% of the pixels in the original image, while they do not cover the main objects in the natural image. Our experiments are performed using four pre-trained DNN models and the ImageNet dataset. We also examine the inaccurate results of the interpretation models through mask and heatmap visualization. The proposed adversarial attack method could be a reference for developing robust network interpretation models that are more reliable for the decision-making process of pre-trained DNN models.