A Novel Integration of Data-Driven Rule Generation and Computational Argumentation for Enhanced Explainable AI

Artificial Intelligence (AI) is a tremendous resource. Undoubtedly the medical profession must be equipped for proper training so that these new technologies can be integrated into day-to-day operations, including clinical activities. Scientific societies, whose mission is to ensure the professional growth of the graduates, and who support their members in their professional life, play an important role in the training courses. The mission of Scientific societies is also to “take them to the future by guaranteeing high skills”, therefore it is essential to move in this direction as AMD has been doing for several years. One of the hallmarks of transparent AI algorithms is that make explicit the patterns and reasoning behind the decisions they make and suggest. This enables a clinician to intervene and to some extent guide the machine’s reasoning. AMD’s choice was to adopt transparent AI solutions, and it has begun a number of projects using its Annali database with the adoption of a Machine Learning tool with clear rules, the Logic Learning Machine, for its analyses. This experience revealed that, in addition to the notable advantages of the speed and efficiency of the analysis process, this technology fulfils a “steering function” guiding analysts and diabetologists in the study, in the in-depth analysis and in interpreting the findings, which may be: explanatory (what is this), predictive (what will be) and scenario simulation (what if). KEY WORDS artificial Intelligence; machine learning; descriptive analysis; predictive analysis; prescriptive analysis; what-if analysis.

A rule-based system can be a solution for context reasoning in context-aware computing systems. In this paper we propose new flexible SoC (System-on-a-Chip) architecture for real-time rule-based system. The proposed architecture can match up values and variables of the left-hand sides of ‘if-then rules' (rule's LHS) in parallel. Compared to previous hardware rule-based system, we reduce the number of constraints on rule representations and combinations of condition terms in rule's LHS by using a modified contents addressable memory and a crossbar switch network (CSN). The modified contents addressable memory (CAM), in which the match operation of the system is processed in parallel, stores the rule-base of the system. The crossbar switch network is located between the input buffer that stores external raw input data and the working memory, and can freely configure condition operation of rule's LHS and working memory with stored data within the input buffer. The proposed SoC systems architecture has been designed and verified in a SoC development platform called SystemC.

Scientific research in the formal sciences comes in multiple degrees of formality: fully formal work; rigorous proofs that practitioners know to be formalizable in principle; and informal work like rough proof sketches and considerations about the advantages and disadvantages of various formal systems. This informal work includes informal and semi-formal debates between formal scientists, e.g. about the acceptability of foundational principles and proposed axiomatizations. In this paper, we propose to use the methodology of structured argumentation theory to produce a formal model of such informal and semi-formal debates in the formal sciences. For this purpose, we propose ASPIC-END, an adaptation of the structured argumentation framework ASPIC+ which can incorporate natural deduction style arguments and explanations. We illustrate the applicability of the framework to debates in the formal sciences by presenting a simple model of some arguments about proposed solutions to the Liar paradox, and by discussing a more extensive—but still preliminary—model of parts of the debate that mathematicians had about the Axiom of Choice in the early twentieth century.

Artificial intelligence (AI) has the potential to transform medical informatics by supporting clinical decision-making, reducing diagnostic errors, and improving workflows and efficiency. However, successful integration of AI-based decision support systems depends on careful consideration of human-AI collaboration, trust, skill maintenance, and automation bias. This work proposes five central questions to guide future research in medical informatics and human-computer interface (HCI). We focus on AI-based clinical decision support systems, including computer vision algorithms for medical imaging (radiology, pathology), natural language processing for structured and unstructured electronic health record (EHR) data, and rule-based systems. Relevant data modalities include clinician-acquired images, EHR text, and increasingly, patient-generated content in telehealth contexts. We review existing evidence regarding diagnostic errors across specialties, the effectiveness and risks of AI tools in reducing perceptual and interpretive errors, and the human factors influencing diagnostic decision-making in AI-enabled contexts. We synthesize insights from medicine, cognitive science, and HCI to identify gaps in knowledge and propose five key questions for continued research. Diagnostic errors remain common across medicine, with AI offering potential to reduce both perceptual and interpretive errors. However, the impact of AI depends critically on how and when information is presented. Studies indicate that delayed or toggleable cues may outperform immediate ones, but attentional capture, overreliance, and bias remain significant risks. Explainable AI provides transparency but can also bias decisions. Long-term reliance on AI may erode clinician skills, particularly for trainees and in low-prevalence contexts. Historical failures of computer-aided diagnosis in mammography highlight these challenges. Effective AI integration requires human-centered and adaptive design. Five central research questions address: (1) what type and format of information AI should provide; (2) when information should be presented; (3) how explainable AI affects diagnostic decisions; (4) how AI influences automation bias and complacency; and (5) the risks of skill decay due to reliance on AI. Each question underscores the importance of balancing efficiency, accuracy, and clinician expertise while mitigating bias and skill degradation. AI holds promise for improving diagnostic accuracy and efficiency, but realizing its potential requires post-deployment evaluation, equitable access, clinician oversight, and targeted training. AI must complement, rather than replace, human expertise, ensuring safe, effective, and sustainable integration into diagnostic decision-making. Addressing these challenges proactively can maximize AI's potential across healthcare and other high-stakes domains.

The rise of sophisticated cyber threats, such as malware and network intrusions, necessitates the use of Artificial Intelligence (AI) for efficient and accurate detection. However, traditional AI models often operate as black boxes, leaving security analysts without insights into the reasoning behind critical decisions. Explainable AI (XAI) addresses this challenge by providing interpretability and transparency in AI-driven cybersecurity solutions. This paper explores the role of XAI in malware analysis and network intrusion detection, highlighting how interpretable models enhance trust, improve decision-making, and facilitate regulatory compliance. It examines state-of-the-art XAI techniques, including Shapley Additive Explanations (SHAP), Local Interpretable Model-agnostic Explanations (LIME), and rule-based systems, for their application in identifying malicious software and detecting network anomalies. Furthermore, the paper discusses challenges, such as computational overhead and scalability, while presenting future directions for integrating XAI in real-time and hybrid security frameworks. By advancing the adoption of interpretable AI, cybersecurity systems can achieve greater effectiveness and reliability, addressing both technical and organizational needs in combating evolving cyber threats.

The rapid proliferation of artificial intelligence (AI) technologies across various industries and decision-making processes has undeniably transformed the way of approaching complex problems and tasks. AI systems have proven their prowess in areas such as healthcare, finance, and autonomous systems, revolutionizing how decisions are made. Nevertheless, this proliferation of AI has raised critical concerns regarding the transparency, accountability, and fairness of these systems, as many of the state-of-the-art AI models often resemble complex black boxes. These intricate models, particularly deep learning neural networks, harbor non-linear relationships that are difficult for human users to decipher, thereby raising concerns about bias, fairness, and overall trustworthiness in AI-driven decisions. The urgency of this issue is underscored by the realization that AI should not merely be accurate; it should also be interpretable. Explainable AI (XAI) has emerged as a vital field of research, emphasizing the development of models and techniques that render AI systems comprehensible and transparent in their decision-making processes. This paper investigates into the relevance and significance of XAI across various domains, including healthcare, finance, and autonomous systems, where the ability to understand the rationale behind AI decisions is paramount. In healthcare, where AI assists in diagnosis and treatment, the interpretability of AI models is crucial for clinicians to make informed decisions. In finance, applications like credit scoring and investment analysis demand transparent AI to ensure fairness and accountability. In the realm of autonomous systems, transparency is indispensable to guarantee safety and compliance with regulations. Moreover, government agencies in areas such as law enforcement and social services require interpretable AI to maintain ethical standards and accountability. This paper also highlights the diverse array of research efforts in the XAI domain, spanning from model-specific interpretability methods to more general approaches aimed at unveiling complex AI models. Interpretable models like decision trees and rule-based systems have gained attention for their inherent transparency, while integrating explanation layers into deep neural networks strives to balance accuracy with interpretability. The study emphasizes the significance of this burgeoning field in bridging the gap between AI's advanced capabilities and human users' need for comprehensible AI systems. It seeks to contribute to this field by exploring the design, development, and practical applications of interpretable AI models and techniques, with the ultimate goal of enhancing the trust and understanding of AI-driven decisions.

The growing use of voice communication in digital platforms has increased the danger of audio-based social engineering attacks as vishing. Traditional detection methods often rely on text-based information or single-language analysis and thus are vulnerable to genuine multilingual attacks in the real world. This research presents a novel audio based, multilingual system for the detection of vishing attacks and AI-generated (deepfake) voices, specifically focusing on English and French languages. Two distinct machine learning models are developed: the first identifies vishing attempts, while the second distinguishes between real and synthetic voices. Audio features such as MFCCs, spectral centroid, chroma STFT, and zero-crossing rate are extracted from voice samples of up to 60 seconds in length were used. To ensure transparency and interpretability in prediction outcomes, Explainable AI (XAI) models were integrated to provide meaning insight. Experimental evaluations demonstrate high accuracy across both languages and highlight the effectiveness of XAI in providing meaningful insights into model decisions. Finally, an inducted rule-based decision system is applied to combine the outputs of both models, enabling a more robust and context-aware classification of audio threats on social media interactions.

The massive proliferation of financial crimes, especially money laundering (ML) and supporting terrorism (TF), is a critical challenge of financial security and stability around the globe. The growing complexity and cross-jurisdictionalism of the illicit world call out a transition to more robust, data-driven compliance systems, not the traditional rule-based systems (RBS). This is a critical review which assiduously examines the status quo with regards to the incorporation of Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) techniques in resolute cybersecurity systems in the context of Anti-Money Laundering (AML) and Counter-Terrorist Financing (CTF) research that has been published in the last 5 years (2020-2025). Based on the ten seminal studies analyzed in detail and with a methodological focus, three fundamental limitations of the system are outlined that include the lack of flexibility and scalability in real time, insufficient unstructured data management, and the inability to consistently adhere to cross-border regulations. To overcome such gaps, the review summarizes the state-of-the-art solutions, i.e., the Dynamic Graph Neural Networks (DGNNs), [1]Federated Learning (FL), and Explainable AI (XAI). The study gives a four-layered, Resilient Multi-Layered Hybrid AML/CTF System that centers on the empirical validation of these combined systems, in which strong cybersecurity solutions are necessary to ensure model integrity to counter adversarial machine learning attacks.

Computational argumentation is primed to strengthen the current hot research field of Explainable Artificial Intelligence (XAI), e.g., by dialectical approaches. In this paper, we extend and discuss a recently proposed approach of so-called strong acceptance on abstract argumentation that aims to support explaining argumentative acceptance. Our goal is to push these results into the realm of structured argumentation. In this setting, a knowledge base induces an abstract argumentation framework (AF) via instantiation. We investigate how and under which conditions it is possible to transfer results regarding strong acceptance between the given knowledge base and the induced AF. To this end we consider generic functions formalizing the interaction of the AF and the knowledge base. This approach helps us to infer rather general results making basic assumptions rather than dealing with the technical details of several structured argumentation formalisms. Along the way, we apply our techniques to the concrete approach of assumption-based argumentation (ABA) which constitutes one of the primal structured argumentation formalisms.

Artificial intelligence and deep learning are powerful tools for extracting knowledge from large datasets, particularly in healthcare. However, their black-box nature raises interpretability concerns, especially in high-stakes applications. Existing eXplainable Artificial Intelligence methods often focus solely on visualization or rule-based explanations, limiting interpretability's depth and clarity. This work proposes a novel explainable AI method specifically designed for medical image analysis, integrating statistical, visual, and rule-based explanations to improve transparency in deep learning models. Statistical features are derived from deep features extracted using a custom Mobilenetv2 model. A two-step feature selection method - zero-based filtering with mutual importance selection - ranks and refines these features. Decision tree and RuleFit models are employed to classify data and extract human-readable rules. Additionally, a novel statistical feature map overlay visualization generates heatmap-like representations of three key statistical measures (mean, skewness, and entropy), providing both localized and quantifiable visual explanations of model decisions. The proposed method has been validated on five medical imaging datasets - COVID-19 radiography, ultrasound breast cancer, brain tumor magnetic resonance imaging, lung and colon cancer histopathological, and glaucoma images - with results confirmed by medical experts, demonstrating its effectiveness in enhancing interpretability for medical image classification tasks.

Background Trust in artificial intelligence (AI) systems is critical for ethical and effective adoption, particularly among non-expert users. This review aimed to identify factors influencing trust and practical considerations for designing explainable AI (XAI) systems. Methods We systematically reviewed the literature following PRISMA 2020 guidelines and using backward and forward citation searches. The primary search was carried out in Web of Science (WoS), with the final search completed in January 2025. Eligible studies were peer-reviewed publications examining trust in AI among non-expert users and/or design considerations for XAI. Exclusion criteria removed studies focused solely on expert users or unrelated to trust or explainability. Results 35 studies involving diverse non-expert populations were included. We used a thematic synthesis approach to identify 33 trust-related factors grouped into personal characteristics, sociocultural influences, design and interaction attributes, and system-level properties (e.g., age, emotions, digital literacy, social norms, usability, aesthetics, explanation type, accuracy, transparency, regulatory compliance). Additionally, 120 design considerations were extracted across nine domains, including type and form of explanation; user experience and interaction; trust, transparency and human oversight; robustness, safety and reliability; data, traceability and the AI lifecycle; regulation and compliance; ethics, values and social responsibility; evaluation methods and metrics; and usage context and organizational factors. Conclusions The review synthesizes emerging perspectives on AI trust and explainability and identifies six domains that warrant further research to support the responsible design and deployment of XAI systems. Limitations include heterogeneous evaluation practices and inconsistent operationalization of trust among non-expert users, which complicates comparability across studies and hinder the responsible deployment of XAI systems.

The term "explainable AI" refers to the goal of producing artificially intelligent agents that are capable of providing explanations for their decisions. Some models (e.g., rule-based systems) are designed to be explainable, while others are less explicit "black boxes" for which their reasoning remains a mystery. One example of the latter is the neural network, and over the past few decades, researchers in the field of neural-symbolic integration (NSI) have sought to extract relational knowledge from such networks. Extraction from deep neural networks, however, has remained a challenge until recent years in which many methods of extracting distinct, salient features from input or hidden feature spaces of deep neural networks have been proposed. Furthermore, methods of identifying relationships between these features have also emerged. This article presents examples of old and new developments in extracting relational explanations in order to argue that the latter have analogies in the former and, as such, can be described in terms of long-established taxonomies and frameworks presented in early neural-symbolic literature. We also outline potential future research directions that come to light from this refreshed perspective.

Web accessibility stands as a fundamental requirement for inclusive financial services because people with disabilities need to access online banking and trading platforms and financial services. The W3C (2025) maintains WCAG 2.1 as a global standard which provides web designers with accessible design guidelines while U.S. and EU regulators enforce compliance through ADA guidance and the 2024 EU Accessibility Act . The majority of websites contain accessibility barriers because research shows that 95% of 1,000,000 websites fail to meet accessibility standards and financial websites become targets for legal actions and regulatory investigations because of their inaccessible design . The process of testing web applications for accessibility through manual methods and rule-based systems (WAVE and axe) proves to be time-consuming and restricted in its capabilities. The research introduces FinAccAI as an AI system which performs automated accessibility testing for financial web applications. The system design implements rule-based verification for WCAG requirements including alt-text and label presence alongside machine learning and deep learning content analysis. The system uses a conceptual algorithm to extract HTML data and perform CNN/NLP-based visual analysis of charts before identifying accessibility problems. The system includes an Explainable AI (XAI) framework which generates human-friendly explanations for each detected violation through LIME/SHAP feature attribution methods . The research evaluates three testing methods (rule-based and ML and DL) through their ability to detect problems and their scope of detection while previous research demonstrates AI systems can decrease human work requirements . The AI-enhanced testing method demonstrates potential to achieve expert-level results according to our conceptual assessment which draws from research on finance site auditing .The system requires additional research to address model bias and generative errors which affect its performance while maintaining open-source model availability for reproducibility. The proposed system creates essential components for automated accessibility testing in financial services which helps in both regulatory compliance as well as business development. The research demonstrates that AI-based accessibility testing identifies more accessibility problems than traditional tools while delivering fast and dependable compliance verification results. The FinAccAI system enables large-scale intelligent accessibility audits which support national digital inclusion initiatives while helping institutions meet regulations and minimizing their exposure to risks and expanding financial services to 10 million American users. The research creates essential foundations for upcoming AI-based accessibility testing research while establishing open accessible solutions which will benefit the U.S. financial and technological sectors.

Phishing attacks are considered to be one of the most widespread cybersecurity threats, and attackers are becoming more successful by using advances in the field of artificial intelligence and natural language generation, in order to deceive consumers via email, SMS, and web. The existing rule-based and heuristic methods of detection cannot keep up with these dynamic and context-sensitive attacks, hence a high false-negative rate. The given work carries out a critical evaluation of the methods of artificial intelligence (AI), natural language processing (NLP)-based phishing detection, and concentrates on the deep learning, explainable artificial intelligence (XAI) methods. It was selected using IEEE Xplore, Scopus, Web of Science, ACM Digital Library, and ScienceDirect according to the PRISMA guidelines and 45 primary studies published between 2017 and 2025. This paper discusses preprocessing techniques, feature extraction techniques, machine learning, deep learning architectures, hybrid detection models, and explainability mechanisms of phishing detection. The findings indicate that hybrid systems incorporating convolutional neural networks, recurrent models, and transformer-based embeddings are able to perform better than traditional classifiers and are able to achieve over 95% accuracy when using various communication channels. Nevertheless, the majority of high-performing models remain opaque and, therefore, cannot be used in controlled cases. This research reveals the following gaps in research: poor cross-platform generalization, inadequate semantic resistance to paraphrased phishing messages, and a lack of explainability incorporation. The article gives a systematic overview of the current methodologies and gives future research directions in explainable, scalable, and adaptable phishing detection systems.

Artificial intelligence (AI) and machine learning (ML) are increasingly being applied in sports science to predict performance, assess injury risk, and support tactical decision-making. However, the opacity of many machine learning (ML) models has led to a growing interest in explainable AI (XAI) methods, which aim to make the decisions of "black box" algorithms more transparent and interpretable. The result of this is an increase in trust, facilitation of model validation, and enablement of more informed decision-making for practitioners and analysts. While XAI is well established in domains like healthcare or finance, its application in sports science remains fragmented and underexplored. This scoping review follows the PRISMA-Sc approach and systematically examines how XAI and interpretable ML techniques have been applied in the context of sports science. Between 2014 and June 2024, a total of 19 studies were identified through a multi-database search and analyzed in terms of sport type, ML model, XAI method, dependent variable, limitations, challenges and future research. The results reveal a clear dominance of SHapley Additive Explanations across multiple disciplines, while other tools such as Gradient-weighted Class Activation Mapping, Individual Conditional Expectation Plots, or domain-specific approaches are rarely used. Visual and rule-based explanation methods were largely absent. The findings highlight a lack of methodological diversity and limited validation of explanations with domain experts or practitioners. To increase real-world impact, future work should explore comparative evaluations of XAI techniques, domain-specific explanation frameworks, and user-centered approaches that align with the needs of coaches, athletes, and analysts.