In recent years, technology has advanced to the fourth industrial revolution (Industry 4.0), where the Internet of things (IoTs), fog computing, computer security, and cyberattacks have evolved exponentially on a large scale. The rapid development of IoT devices and networks in various forms generate enormous amounts of data which in turn demand careful authentication and security. Artificial intelligence (AI) is considered one of the most promising methods for addressing cybersecurity threats and providing security. In this study, we present a systematic literature review (SLR) that categorize, map and survey the existing literature on AI methods used to detect cybersecurity attacks in the IoT environment. The scope of this SLR includes an in-depth investigation on most AI trending techniques in cybersecurity and state-of-art solutions. A systematic search was performed on various electronic databases (SCOPUS, Science Direct, IEEE Xplore, Web of Science, ACM, and MDPI). Out of the identified records, 80 studies published between 2016 and 2021 were selected, surveyed and carefully assessed. This review has explored deep learning (DL) and machine learning (ML) techniques used in IoT security, and their effectiveness in detecting attacks. However, several studies have proposed smart intrusion detection systems (IDS) with intelligent architectural frameworks using AI to overcome the existing security and privacy challenges. It is found that support vector machines (SVM) and random forest (RF) are among the most used methods, due to high accuracy detection another reason may be efficient memory. In addition, other methods also provide better performance such as extreme gradient boosting (XGBoost), neural networks (NN) and recurrent neural networks (RNN). This analysis also provides an insight into the AI roadmap to detect threats based on attack categories. Finally, we present recommendations for potential future investigations.

The prevalence of cyberbullying on Social Media (SM) platforms has become a significant concern for individuals, organizations, and society as a whole. The early detection and intervention of cyberbullying on social media are critical to mitigating its harmful effects. In recent years, ensemble learning has shown promising results for detecting cyberbullying on social media. This paper presents an ensemble stacking learning approach for detecting cyberbullying on Twitter using a combination of Deep Neural Network methods (DNNs). It also introduces BERT-M, a modified BERT model. The dataset used in this study was collected from Twitter and preprocessed to remove irrelevant information. The feature extraction process involved utilizing word2vec with Continuous Bag of Words (CBOW) to form the weights in the embedding layer. These features were then fed into a convolutional and pooling mechanism, effectively reducing their dimensionality, and capturing the position-invariant characteristics of the offensive words. The validation of the proposed stacked model and BERT-M was performed using well-known model evaluation measures. The stacked model achieved an F1-score of 0.964, precision of 0.950, recall of 0.92 and the detection time reported was 3 min, which surpasses the previously reported accuracy and speed scores for all known NLP detectors of cyberbullying, including standard BERT and BERT-M. The results of the experiment showed that the stacking ensemble learning approach achieved an accuracy of 97.4% in detecting cyberbullying on Twitter dataset and 90.97% on combined Twitter and Facebook dataset. The results demonstrate the effectiveness of the proposed stacking ensemble learning approach in detecting cyberbullying on SM and highlight the importance of combining multiple models for improved performance.

Industry 4.0 (I4.0) is a technological development in the manufacturing industry that has revolutionized Total Quality Management (TQM) practices. There has been scant empirical research on the multidimensional perspective of TQM. Thus, this study aims to empirically examine the effect of the multidimensional view of TQM (soft and hard) on I4.0 readiness in small and medium-sized (SMEs) manufacturing firms. Based on the sociotechnical systems (STS) theory, a framework has been developed and validated empirically through an online survey of 209 Malaysian SMEs manufacturing firms. Unlike the existing TQM studies that used structural equation modeling (SEM), a two-stage analysis was performed in this study. First, the SEM approach was used to determine which variable significantly affects I4.0 readiness. Second, the artificial neural network (ANN) technique was adopted to rank the relative influence of significant predictors obtained from SEM. The results show that the soft and hard TQM practices have supported the I4.0 readiness. Moreover, the results highlight that hard TQM practices have mediating role between soft TQM practices and I4.0 readiness. The ANN results affirmed that customer focus is considered an important TQM factor for I4.0 managerial readiness, advanced manufacturing technology for operational readiness and top management commitment for technology readiness. In a nutshell, the SEM-ANN approach uniquely contributes to the TQM and I4.0 literature. Finally, the findings can help managers to prioritize firms’ soft and hard quality practices that promote I4.0 implementation, especially in emerging economies.

Large Language Models (LLMs) are increasingly integrated into AI-powered mobile applications, offering novel functionalities but also introducing the risk of “hallucinations” generating plausible yet incorrect or nonsensical information. These AI errors can significantly degrade user experience and erode trust. However, there is limited empirical understanding of how users perceive, report, and are impacted by LLM hallucinations in real-world mobile app settings. This paper presents a large-scale empirical study analyzing 3 million user reviews from 90 diverse AI-powered mobile apps to characterize these user-reported issues. Using a mixed-methods approach, a heuristic-based User-Reported LLM Hallucination Detection algorithm were applied to identify 20,000 candidate reviews, from which 1,000 are manually annotated. This analysis estimates the prevalence of user reports indicative of LLM hallucinations, which was found to be approximately 1.75% within reviews initially flagged as relevant to AI errors. A data-driven taxonomy of seven user-perceived LLM hallucination types, were developed with Factual Incorrectness (H1) emerged as the most frequently reported type, accounting for 38% of instances, followed by Nonsensical/Irrelevant Output (H3) at 25%, and Fabricated Information (H2) at 15%. Furthermore, linguistic patterns were identified using N-grams generation, Non-Negative Matrix Factorization (NMF) topics and sentiment characteristics using VADER, showing significantly lower scores for hallucination reports associated with these reviews. These findings offer critical implications for software quality assurance, highlighting the need for targeted monitoring and mitigation strategies for AI mobile apps. This research provides a foundational, user-centric understanding of LLM hallucinations, paving the way for improved AI model development and more trustworthy mobile applications.

Digital-only banks have not achieved adoption expectations despite being one of the latest innovations in fintech. Several digital-only banks in the United States and Japan have gone bankrupt, and others continue to operate at a loss. Therefore, it is imperative to conduct this study in Malaysia to understand customers’ behavior, particularly regarding the adoption of digital-only banks. With climate change, environmental-friendly behavior, which has been ignored in digital-only bank literature, is becoming increasingly pertinent. This study addresses the lack of an integrated model that investigates the effect of external factors (i.e., critical mass, number of services, and environmental concerns), customer self-determination factors (i.e., trust), and mental perceptions of technology adoption (i.e., convenience, economic efficiency, functional and security risks, as well as perceived value) on the intention to adopt digital-only banks. Data were collected through an online survey targeting Klang Valley residents in the prime age range of 25–54 years old using stratified random sampling. The data was analyzed using structural equation modeling by performing confirmatory factor analysis (CFA) and SEM path analysis in AMOS.v26 software. The results show that convenience, economic efficiency, number of services, trust, perceived value, and environmental concern all have positive significant relationships with the intention to adopt digital-only banks. Further, environmental concern is the strongest indicator of behavioral intention. In contrast, functional and security risks have a negative but non-significant relationship with the intention to adopt digital-only banks. Finally, critical mass has a positive but non-significant effect on the behavioral intention. This study is among the first to examine the influence of environmental concern on behavioral intentions in a digital-only banking context. It also contributes to an expanding body of research investigating environmental sustainability by presenting empirical results in the context of digital-only banks.

Since social media platforms are widely used and popular, they have given us more opportunities than we can even imagine. Despite all of the known benefits, some users may abuse these opportunities to humiliate, insult, bully, and harass other people. This issue explains why there is a need to reduce such negative activities and create a safe cyberspace for innocent people by detecting cyberbullying activity. This study provides a comparative analysis of deep learning methods used to test and evaluate their effectiveness regarding a well-known global Twitter dataset. To recognize abusive tweets and overcome existing challenges, attention-based deep learning methods are introduced. The word2vec with CBOW concatenated formed the weights included in the embedding layer and was used to extract the features. The feature vector was input into a convolution and pooling mechanism, reducing the feature dimensionality while learning the position-invariant of the offensive words. A SoftMax function predicts feature classification. Using benchmark experimental datasets and well-known evaluation measures, the convolutional neural network model with attention-based long- and short-term memory was found to outperform other DL methods. The proposed cyberbullying detection methods were evaluated using benchmark experimental datasets and well-known evaluation measures. Finally, the results demonstrated the superiority of the attention-based 1D convolutional long short-term memory (Conv1DLSTM) classifier over the other implemented methods.