The lack of interpretability in AI-based intrusion detection systems poses a critical barrier to their adoption in forensic cybersecurity, which demands high levels of reliability and verifiable evidence. To address this challenge, the integration of explainable artificial intelligence (XAI) into forensic cybersecurity offers a powerful approach to enhancing transparency, trust, and legal defensibility in network intrusion detection. This study presents a comparative analysis of SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) applied to Extreme Gradient Boosting (XGBoost) and Attentive Interpretable Tabular Learning (TabNet), using the UNSW-NB15 dataset. XGBoost achieved 97.8% validation accuracy and outperformed TabNet in explanation stability and global coherence. In addition to classification performance, we evaluate the fidelity, consistency, and forensic relevance of the explanations. The results confirm the complementary strengths of SHAP and LIME, supporting their combined use in building transparent, auditable, and trustworthy AI systems in digital forensic applications.

In recent years, there has been growing interest in the use of computer-assisted technology for early detection of skin cancer through the analysis of dermatoscopic images. However, the accuracy illustrated behind the state-of-the-art approaches depends on several factors, such as the quality of the images and the interpretation of the results by medical experts. This systematic review aims to critically assess the efficacy and challenges of this research field in order to explain the usability and limitations and highlight potential future lines of work for the scientific and clinical community. In this study, the analysis was carried out over 45 contemporary studies extracted from databases such as Web of Science and Scopus. Several computer vision techniques related to image and video processing for early skin cancer diagnosis were identified. In this context, the focus behind the process included the algorithms employed, result accuracy, and validation metrics. Thus, the results yielded significant advancements in cancer detection using deep learning and machine learning algorithms. Lastly, this review establishes a foundation for future research, highlighting potential contributions and opportunities to improve the effectiveness of skin cancer detection through machine learning.

Teaching methods for calculation and project development, focusing on theoretical principles and the reproduction of validated procedures, has been the traditional focus of engineering education. Innovation has been present in universities, mainly in the creation of processes and technologies for the development of products, services, or companies, based on entrepreneurship. Training in innovation has been limited to interested students, and not encouraged for all students, despite how relevant it is for current and future global development. According to the literature research and the opinion of the experts, this research identifies the characteristics of innovation that engineering students should acquire, in response to the challenges of engineering in the 21st century, considering as a basis the Sustainable Development Goals (SDGs), in the context of the increasingly demanding requirements of industry 4.0. The identification of the relevant aspects in innovation were categorized according to the expertise and academic performance of the authors. In addition to this, the investigation of the representative elements of Industry 4.0, and the incorporation of Sustainable Development Goals, establish the basis of this study to guide the development of innovation skills in the process of engineering student education. Furthermore, in order to integrate innovation skills, elements of Industry 4.0 and aspects of Sustainable Development Goals, the concept of competence is introduced, with a conceptual structure that considers knowledge, attitude and performance context, thus this research provides a conceptual framework for those interested in constructing innovation skills in engineering, oriented towards the development of an innovation culture and mentality, as part of the expected professional performance.

Malicious Software, commonly known as Malware, represents a persistent threat to cybersecurity, targeting the confidentiality, integrity, and availability of information systems. The digital era, marked by the proliferation of connected devices, cloud services, and the advancement of machine learning, has brought numerous benefits; however, it has also exacerbated exposure to cyber threats, affecting both individuals and corporations. This systematic review, which follows the PRISMA 2020 framework, aims to analyze current trends and new methods for malware detection and classification. The review was conducted using data from Web of Science and Scopus, covering publications from 2020 and 2024, with over 47 key studies selected for in-depth analysis based on relevance, empirical results and citation metrics. These studies cover a variety of detection techniques, including machine learning, deep learning and hybrid models, with a focus on feature extraction, malware behavior analysis and the application of advanced algorithms to improve detection accuracy. The results highlight important advances, such as the improved performance of ensemble learning and deep learning models in detecting sophisticated threats. Finally, this study identifies the main challenges and outlines opportunities of future research to improve malware detection and classification frameworks.

El objetivo de investigación es identificar las habilidades de innovación que los futuros ingenieros deben adquirir en respuesta a los desafíos de la ingeniería del siglo XXI, los requisitos de la actual industria 4.0 y los objetivos de desarrollo sostenible (ODS). El método está organizado en dos etapas: 1) identificación de las características de la innovación y 2) construcción de habilidades de innovación para los estudiantes de ingeniería. Esta investigación esta basada en una revisión de literatura en Web of Science y Scopus desde el año 2000 hasta el presente. Se plantea un modelo que integra los ODSs en el contexto de la industria 4.0 y las habilidades de innovación en el ámbito de ingeniería. Se concluye que el modelo descrito aquí es una representación concreta que permite integrar los conceptos relacionados con los objetivos de desarrollo sostenible y la industria 4.0 para incorporarlos en el ámbito de la educación universitaria.

The increase in malicious cyber activities has generated the need to produce effective tools for the field of digital forensics and incident response. Artificial intelligence (AI) and its fields, specifically machine learning (ML) and deep learning (DL), have shown great potential to aid the task of processing and analyzing large amounts of information. However, models generated by DL are often considered “black boxes”, a name derived due to the difficulties faced by users when trying to understand the decision-making process for obtaining results. This research seeks to address the challenges of transparency, explainability, and reliability posed by black-box models in digital forensics. To accomplish this, explainable artificial intelligence (XAI) is explored as a solution. This approach seeks to make DL models more interpretable and understandable by humans. The SHAP (SHapley Additive eXplanations) and LIME (Local Interpretable Model-agnostic Explanations) methods will be implemented and evaluated as a model-agnostic technique to explain predictions of the generated models for forensic analysis. By applying these methods to the XGBoost and TabNet models trained on the UNSW-NB15 dataset, the results indicated distinct global feature importance rankings between the model types and revealed greater consistency of local explanations for the tree-based XGBoost model compared to the deep learning-based TabNet. This study aims to make the decision-making process in these models transparent and to assess the confidence and consistency of XAI-generated explanations in a forensic context.