<b>Artificial intelligence-driven phishing detection using natural language processing </b>

Phishing attacks are a persistent cybersecurity threat, exploiting human vulnerabilities via deceptive emails and malicious URLs. This project introduces a novel Reinforcement Learning (RL)-based system to automate phishing detection and response. By employing advanced RL algorithms, such as Deep Q-Learning and Policy Gradient methods, the system dynamically learns to identify phishing indicators within email content and URLs through Natural Language Processing (NLP) and feature extraction techniques. The RL agent continuously adapts its detection strategies based on evolving threats and user feedback, aiming to minimize false positives while accurately identifying malicious activities. Upon detecting potential threats, the system initiates automated responses, including alert notifications, URL blocking, and user warnings, thereby enhancing security measures. Implementing this RL-based solution within Security Operations Centers (SOCs) or email security platforms offers a scalable, real-time defense against phishing attacks. This approach effectively safeguards sensitive information and strengthens organizational resilience against cyber threats.

Detecting phishing websites is a rapidly evolving field aimed at identifying and mitigating cyberattacks targeting individuals, organizations, and governments. Ongoing progress in artificial intelligence (AI) has the potential to revolutionize phishing detection by enhancing model accuracy and improving transparency through eXplainable AI (XAI). However, significant challenges remain, particularly in integrating feature engineering with XAI to address sophisticated phishing strategies including zero-day attacks, that evade traditional detection mechanisms. To overcome these challenges, this examines the impact of feature engineering and XAI in phishing detection, emphasizing their ability to enhance accuracy while providing interpretability. By integrating feature extraction with interpretable models, these techniques improve decision-making transparency and system robustness. This paper presents the first systematic literature review (SLR) focusing on the impact of feature engineering and XAI on state-of-the-art phishing detection approaches. Additionally, it identifies critical research gaps and challenges, including scalability issues, the evolution of phishing techniques, and balancing complexity with interpretability. The findings provide valuable academic insights while offering practical recommendations for developing accurate and interpretable phishing detection systems, aiding organizations in strengthening cybersecurity measures.

To review studies of Natural Language Processing (NLP) systems that assist in cancer care, explore use cases and summarise current research progress. A scoping review, searching six databases (1) MEDLINE, (2) Embase, (3) IEEE Xplore, (4) ACM Digital Library, (5) Web of Science, and (6) ACL Anthology. Studies were included that reported NLP systems that had been used to improve cancer management by patients or clinicians. Studies were synthesised descriptively and using content analysis. Twenty-nine studies were included. Studies mainly applied NLP in mixed cancer types (n=10, 34.48%) and breast cancer (n=8, 27.59%). NLP was used in four main ways: (1) to support patient education and self-management; (2) to improve efficiency in clinical care by summarising, extracting, and categorising data, and supporting record-keeping; (3) to support prevention and early detection of patient problems or cancer recurrence; and (4) to improve cancer treatment by supporting clinicians to make evidence-based treatment decisions. Studies highlighted a wide variety of use cases for NLP technologies in cancer care. However, few technologies have been evaluated within clinical settings, none have been evaluated against clinical outcomes, and none have been implemented into clinical care. NLP has the potential to improve cancer care via several mechanisms, including information extraction and classification, which could enable automation and personalization of care processes. Additionally, NLP tools such as chatbots show promise in improving patient communication and support. However, there are deficiencies in the evaluation and clinical integration challenges. Interdisciplinary collaboration between computer scientists and clinicians will be essential if NLP technologies are to fulfil their potential to improve patient experience and outcomes. Registered Protocol: https://doi.org/10.17605/OSF.IO/G9DSR.

This study develops a conceptual model for evaluating AI-driven predictive maintenance (PdM) in SCADA-integrated smart grid systems through a systematic review and meta-analysis conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines. A structured search across six major databases, IEEE Xplore, Scopus, Web of Science, ScienceDirect, ACM Digital Library, and Google Scholar, covering the period from January 2013 to December 2024 yielded 4,847 initial records, of which 63 studies met the full inclusion criteria following rigorous dual-reviewer screening, quality appraisal using the Newcastle-Ottawa Scale, and risk-of-bias assessment; pooled effect sizes were subsequently computed using a random-effects model (DerSimonian-Laird estimator) to account for inter-study heterogeneity (I² = 78.4%), with subgroup analyses stratified by AI algorithm type, grid segment, and SCADA integration depth. Meta-analytic findings revealed a weighted mean fault detection accuracy of 94.3% (95% CI: 92.1%–96.5%), with deep learning architectures — particularly LSTM and hybrid CNN-LSTM models — significantly outperforming traditional machine learning approaches (SMD = 0.67; 95% CI: 0.48–0.86, p < 0.001), and real-time SCADA-integrated configurations demonstrating markedly greater reductions in unplanned outage rates (SMD = 0.81; 95% CI: 0.59–1.03) relative to offline processing alternatives, with no significant publication bias detected via Egger's test (p = 0.16). Grounded in this synthesized evidence, the study proposes the SCADA-AI Predictive Maintenance Evaluation Framework (SAPMEF), a five-dimensional conceptual model encompassing data acquisition and sensor integration, AI model architecture selection, real-time SCADA communication fidelity, maintenance decision optimization, and grid resilience metrics, offering researchers, grid operators, and policymakers a structured, evidence-based instrument for benchmarking and deploying intelligent PdM solutions, while identifying cybersecurity resilience, model interpretability, and cross-grid transferability as critical priorities for future research.

Artificial intelligence (AI) has, in the recent past, experienced a rebirth with the growth of generative AI systems such as ChatGPT and Bard. These systems are trained with billions of parameters and have enabled widespread accessibility and understanding of AI among different user groups. Widespread adoption of AI has led to the need for understanding how machine learning (ML) models operate to build trust in them. An understanding of how these models generate their results remains a huge challenge that explainable AI seeks to solve. Federated learning (FL) grew out of the need to have privacy-preserving AI by having ML models that are decentralized but still share model parameters with a global model. This study sought to examine the extent of development of the explainable AI field within the FL environment in relation to the main contributions made, the types of FL, the sectors it is applied to, the models used, the methods applied by each study, and the databases from which sources are obtained. A systematic search in 8 electronic databases, namely, Web of Science Core Collection, Scopus, PubMed, ACM Digital Library, IEEE Xplore, Mendeley, BASE, and Google Scholar, was undertaken. A review of 26 studies revealed that research on explainable FL is steadily growing despite being concentrated in Europe and Asia. The key determinants of FL use were data privacy and limited training data. Horizontal FL remains the preferred approach for federated ML, whereas post hoc explainability techniques were preferred. There is potential for development of novel approaches and improvement of existing approaches in the explainable FL field, especially for critical areas. OSF Registries 10.17605/OSF.IO/Y85WA; https://osf.io/y85wa.

Abstract—Phishing attacks have evolved beyond deceptive URLs to include malicious emails, QR codes, images, and text, posing serious cybersecurity threats. This research presents a multi-modal phishing detection framework that leverages Princi- pal Component Analysis (PCA) for dimensionality reduction and ensemble learning models—Random Forest and XGBoost—for accurate classification of fraudulent content. The system analyzes diverse inputs, including URLs, QR codes, and textual data, stored and processed through serialized .pkl datasets. Imple- mented using Python and Flask, the framework integrates Ex- plainable AI techniques (SHAP, LIME) for model transparency. Experimental results demonstrate high accuracy, efficiency, and interpretability, offering a scalable solution for detecting phishing threats across multiple digital communication channels. Index Terms—Key words: Phishing Detection, PCA, Random Forest, XGBoost, Explainable AI, QR Code Security, Cyberse- curity, .pkl Datasets.

Phishing attacks continue to grow in scale and sophistication, causing substantial financial losses and privacy breaches worldwide. Recent advances in large language models (LLMs) have brought significant changes to the generation and detection of phishing content. This study systematically investigates the dual role of LLMs in facilitating phishing attacks and strengthening countermeasures. Using the PRISMA methodology, authors screened 142 records published between January 2023 and April 2025 and identified 36 eligible studies from major academic databases, including IEEE Xplore, ScienceDirect, ACM Digital Library, Web of Science, and Scopus. A comprehensive and rigorous analysis was conducted of research trends/themes over time, dataset characteristics, and the LLM architectures/models employed. The findings reveal that most studies relied on manually generated datasets rather than publicly available benchmark datasets, and that GPT-based models received considerably more attention than other LLM architectures. The review demonstrates that LLMs substantially enhance the generation of phishing content by producing coherent, contextually relevant, and persuasive email and website content. This capability lowers the technical barrier for attackers and potentially increases attack effectiveness. Conversely, LLMs also strengthen defensive strategies by enabling more effective analysis of textual and visual content for phishing detection. In many cases, LLM-based approaches outperform traditional machine learning and deep learning methods and, in certain contexts, approach or match human-level performance. Overall, the findings suggest that LLMs have accelerated and automated phishing-related processes, simultaneously intensifying the threat landscape and advancing defensive capabilities. • The first in-depth study to review LLMs usage in Phishing attack generation and detection. • The study reveals LLMs have accelerated and automated phishing-related processes, elevating both threats and defence mechanisms. • GenAI-based multimodal phishing attacks are on the rise due to the wider adoption of GenAI tools in general.

The rapid evolution of Artificial Intelligence (AI) has profoundly impacted IT support services, leading to a paradigm shift from traditional, hierarchical support structures to integrated, human-AI collaborative ecosystems. In these emerging models, AI systems complement human expertise by automating routine tasks, enabling predictive service responses, and enhancing decision accuracy, while human agents contribute contextual judgment, ethical oversight, and emotional intelligence. This systematic review investigates how such collaboration is transforming IT support operations, focusing specifically on its influence on user experience (UX), workflow automation, human cognitive adaptation, and institutional readiness. Adhering to the PRISMA 2020 guidelines, a total of 98 peer-reviewed articles published between 2013 and 2024 were rigorously identified, screened, and synthesized from leading academic databases including Scopus, Web of Science, IEEE Xplore, and ACM Digital Library. The reviewed literature reveals that AI technologies—such as chatbots, machine learning-driven ticketing systems, robotic process automation (RPA), and natural language processing (NLP)—have become central to the modern support landscape, improving first-contact resolution rates, reducing operational costs, and enabling 24/7 support scalability. The review further maps adoption patterns using established theoretical frameworks such as the Technology Acceptance Model (TAM), Unified Theory of Acceptance and Use of Technology (UTAUT), and various digital transformation models, all of which highlight key enablers like performance expectancy, ease of use, social influence, and strategic alignment. Despite promising outcomes, persistent challenges remain—including data fragmentation, algorithmic bias, interface limitations, and workforce resistance to automation—which must be addressed through thoughtful design and ethical governance. By synthesizing insights across technical, human, and organizational dimensions, this review contributes a comprehensive and interdisciplinary understanding of how human-AI collaboration is redefining IT support services, offering practical implications for researchers, system designers, and IT leaders seeking to deploy intelligent, sustainable, and user-centric support systems.

<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Context:</i> User stories have been widely accepted as artifacts to capture the user requirements in agile software development. They are short pieces of texts in a semi-structured format that express requirements. Natural language processing (NLP) techniques offer a potential advantage in user story applications. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Objective:</i> Conduct a systematic literature review to capture the current state-of-the-art of NLP research on user stories. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Method:</i> The search strategy is used to obtain relevant papers from SCOPUS, ScienceDirect, IEEE Xplore, ACM Digital Library, SpringerLink, and Google Scholar. Inclusion and exclusion criteria are applied to filter the search results. We also use the forward and backward snowballing techniques to obtain more comprehensive results. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Results:</i> The search results identified 718 papers published between January 2009 to December 2020. After applying the inclusion/exclusion criteria and the snowballing technique, we identified 38 primary studies that discuss NLP techniques in user stories. Most studies used NLP techniques to extract aspects of who, what, and why from user stories. The purpose of NLP studies in user stories is broad, ranging from discovering defects, generating software artifacts, identifying the key abstraction of user stories, and tracing links between model and user stories. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Conclusion:</i> NLP can help system analysts manage user stories. Implementing NLP in user stories has many opportunities and challenges. Considering the exploration of NLP techniques and rigorous evaluation methods is required to obtain quality research. As with NLP research in general, the ability to understand a sentence’s context continues to be a challenge.

BackgroundResponsible artificial intelligence (RAI) emphasizes the use of ethical frameworks implementing accountability, responsibility, and transparency to address concerns in the deployment and use of artificial intelligence (AI) technologies, including privacy, autonomy, self-determination, bias, and transparency. Standards are under development to guide the support and implementation of AI given these considerations.ObjectiveThe purpose of this review is to provide an overview of current research evidence and knowledge gaps regarding the implementation of RAI principles and the occurrence and resolution of ethical issues within AI systems.MethodsA scoping review following Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) guidelines was proposed. PubMed, ERIC, Scopus, IEEE Xplore, EBSCO, Web of Science, ACM Digital Library, and ProQuest (Arts and Humanities) will be systematically searched for articles published since 2013 that examine RAI principles and ethical concerns within AI. Eligibility assessment will be conducted independently and coded data will be analyzed along themes and stratified across discipline-specific literature.ResultsThe results will be included in the full scoping review, which is expected to start in June 2024 and completed for the submission of publication by the end of 2024.ConclusionsThis scoping review will summarize the state of evidence and provide an overview of its impact, as well as strengths, weaknesses, and gaps in research implementing RAI principles. The review may also reveal discipline-specific concerns, priorities, and proposed solutions to the concerns. It will thereby identify priority areas that should be the focus of future regulatory options available, connecting theoretical aspects of ethical requirements for principles with practical solutions.International Registered Report Identifier (IRRID)PRR1-10.2196/52349

A phishing attack is a threat based on fraudulent communication, usually by e-mail, where the cybercriminals, impersonating a trusted person or organization, try to lure and coax a target. Phishing detection approaches that obtain highly representational features from the text of these e-mails are a suitable strategy to counter these threats since these features can be used to train machine learning algorithms, thus generating models able to classify mail samples as phishing or legitimate messages. This paper proposes a multi-stage approach to detect phishing e-mail attacks using natural language processing and machine learning. The proposed multi-stage approach consists of feature engineering within natural language processing, lemmatization, feature selection, feature extraction, improved learning techniques for resampling and cross-validation, and the configuration of hyperparameters. We present two methods of the proposed approach, the first one exploiting the Chi-Square statistics and the Mutual Information to improve the dimensionality reduction, while the second method associates Principal Component Analysis (PCA) and Latent Semantic Analysis (LSA). Both methods handle the problems of the “curse of dimensionality”, the sparsity, and the amount of information that must be obtained from the context in the Vector Space Model (VSM) representation. These methods yield reduced feature sets that, combined with the XGBoost and Random Forest machine learning algorithms, lead to an F1-measure of 100% success rate, for validation tests with the SpamAssassin Public Corpus and the Nazario Phishing Corpus datasets. Even considering just the text in e-mail bodies, the proposed multi-stage phishing detection approach outperforms state-of-the-art schemes for an accredited data set, requiring a much smaller number of features and presenting lower computational cost.

BackgroundThe rapid evolution of large language models (LLMs) has ushered in a new era of artificial intelligence (AI) with unprecedented capabilities in understanding and generating human-like text. This progress has sparked a burgeoning interest in applying LLMs across diverse fields, including healthcare. However, the use of LLMs in mental health remains a complex area that demands rigorous investigation. This systematic scoping review aims to explore the current landscape of LLM applications in mental health, identify key research trends and gaps, and delineate the ethical and practical boundaries, thereby providing a comprehensive framework for future research and clinical practice.MethodsThis study adheres to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. A comprehensive search was conducted across eleven databases (Web of Science, Scopus, PubMed, Medline, CINAHL, Cochrane, ACM Digital Library, IEEE Xplore, ScienceDirect, APA PsycInfo, and Google Scholar). A total of 29 articles were ultimately included in the study.ResultsThe application of LLMs in mental health is strategically focused on high-throughput screening and clinical augmentation. The application landscape is characterized by domain specialization, with the focus shifting from general models to specialized BERT models to achieve higher clinical accuracy, particularly for high-prevalence disorders such as depression and high-risk conditions. Data analysis is powered by massive, unstructured corpora from social media, supplemented by the systematic incorporation of structured clinical knowledge. However, significant limitations exist, including insufficient cultural sensitivity in non-Western contexts, challenges in capturing longitudinal patient history, and critical risks related to model value alignment and the generation of clinically misleading information.ConclusionLLMs have emerged as sophisticated “Mental Health Agents” with immense potential for providing personalized, knowledge-guided interventions. The core challenge for future development is to transcend basic functionality and achieve clinical rigor. Future research must prioritize deep specialization into psychological models, enhance multimodal integration for comprehensive patient assessment, and urgently develop robust ethical and cultural adaptation frameworks to ensure the models are safe, globally equitable, and reliable for clinical deployment, thereby fulfilling their potential to alleviate the global mental health resource crisis.

The rapid growth of the Internet and the increasing reliance on digital systems have significantly expanded the global digital footprint, creating new challenges for cybersecurity. Artificial Intelligence (AI) technologies, particularly Machine Learning (ML) and Deep Learning (DL), have become central to addressing these challenges by enabling the automation of complex and data-intensive tasks across antivirus solutions, intrusion prevention systems, threat intelligence platforms, and email security tools. While these technologies provide high levels of accuracy in detecting anomalies, malware, and other forms of malicious activity, they are often criticized for operating as “black-box” systems. The lack of interpretability in their decision-making processes limits the ability of cybersecurity professionals to fully understand, validate, and trust the outcomes of AI-driven models, thereby restricting their practical adoption in high-stakes environments. To mitigate these limitations, Explainable Artificial Intelligence (XAI) has emerged as a promising paradigm that aims to make AI outputs transparent, interpretable, and actionable. By providing human-understandable explanations of automated decisions, XAI can bridge the gap between technical performance and practitioner usability, enabling analysts to make informed decisions, improve incident response, and strengthen organizational resilience against both known and emerging threats. This paper reviews recent state-of-the-art developments in XAI for cybersecurity, with a particular emphasis on anomaly detection a critical area for identifying insider threats, zero-day exploits, and atypical system behavior. The review follows a structured literature analysis of peer-reviewed studies published between 2018 and 2025, identified through systematic searches in major academic databases including IEEE Xplore, Scopus, Web of Science, and ACM Digital Library. After applying predefined inclusion and exclusion criteria focused on XAI applications in cybersecurity, 53 relevant studies were analysed to synthesize methodological trends, application domains, and evaluation practices. Drawing on these findings, the paper consolidates fragmented research contributions, identifies current gaps, and provides recommendations for advancing the design and adoption of explainable, trustworthy AI systems in cybersecurity. The analysis further highlights a critical deployment challenge: the integration of explainability mechanisms often introduces trade-offs between predictive accuracy, computational efficiency, and real-time scalability factors that are essential in operational cybersecurity environments.

Phishing websites are still a major threat in today's Internet ecosystem. Despite numerous previous efforts, similarity-based detection methods do not offer sufficient protection for the trusted websites, in particular against unseen phishing pages. This paper contributes VisualPhishNet, a new similarity-based phishing detection framework, based on a triplet Convolutional Neural Network (CNN). VisualPhishNet learns profiles for websites in order to detect phishing websites by a similarity metric that can generalize to pages with new visual appearances. We furthermore present VisualPhish, the largest dataset to date that facilitates visual phishing detection in an ecologically valid manner. We show that our method outperforms previous visual similarity phishing detection approaches by a large margin while being robust against a range of evasion attacks.

Phishing detection with high-performance accuracy and low computational complexity has always been a topic of great interest. New technologies have been developed to improve the phishing detection rate and reduce computational constraints in recent years. However, one solution is insufficient to address all problems caused by attackers in cyberspace. Therefore, the primary objective of this paper is to analyze the performance of various deep learning algorithms in detecting phishing activities. This analysis will help organizations or individuals select and adopt the proper solution according to their technological needs and specific applications’ requirements to fight against phishing attacks. In this regard, an empirical study was conducted using four different deep learning algorithms, including deep neural network (DNN), convolutional neural network (CNN), Long Short-Term Memory (LSTM), and gated recurrent unit (GRU). To analyze the behaviors of these deep learning architectures, extensive experiments were carried out to examine the impact of parameter tuning on the performance accuracy of the deep learning models. In addition, various performance metrics were measured to evaluate the effectiveness and feasibility of DL models in detecting phishing activities. The results obtained from the experiments showed that no single DL algorithm achieved the best measures across all performance metrics. The empirical findings from this paper also manifest several issues and suggest future research directions related to deep learning in the phishing detection domain.