A robust statistical framework for cyber-vulnerability prioritisation under partial information in threat intelligence DOI Creative Commons
Mario Angelelli, Serena Arima, Christian Catalano

и другие.

Expert Systems with Applications, Год журнала: 2024, Номер 255, С. 124572 - 124572

Опубликована: Июнь 25, 2024

Proactive cyber-risk assessment is gaining momentum due to the wide range of sectors that can benefit from prevention cyber-incidents by preserving integrity, confidentiality, and availability data. The rising attention cybersecurity also results increasing connectivity cyber–physical systems, which generates multiple sources uncertainty about emerging cyber-vulnerabilities. This work introduces a robust statistical framework for quantitative qualitative reasoning under cyber-vulnerabilities their prioritisation. Specifically, we take advantage mid-quantile regression deal with ordinal risk assessments, compare it current alternatives ranking graded responses. For this purpose, identify novel accuracy measure suited rank invariance partial knowledge whole set existing vulnerabilities. model tested on both simulated real data selected databases support evaluation, exploitation, or response in realistic contexts. Such datasets allow us models measures, discussing implications threat intelligence decision-making operational scenarios.

Язык: Английский

Conceptual structure and thematic evolution in partial least squares structural equation modeling research DOI Creative Commons
Mario Angelelli, Enrico Ciavolino, Christian M. Ringle

и другие.

Quality & Quantity, Год журнала: 2025, Номер unknown

Опубликована: Март 6, 2025

Язык: Английский

Процитировано

0
A Conceptual Framework for Digital Twin in Healthcare: Evidence from a Systematic Meta-Review DOI Creative Commons
Giulia Pellegrino, Massimiliano Gervasi, Mario Angelelli

и другие.

Information Systems Frontiers, Год журнала: 2024, Номер unknown

Опубликована: Сен. 12, 2024

Язык: Английский

Процитировано

2
Uncertainty‐guided U‐Net for soil boundary segmentation using Monte Carlo dropout DOI Creative Commons
Xiaofang Zhou, Brian Sheil, Stephen K. Suryasentana

и другие.

Computer-Aided Civil and Infrastructure Engineering, Год журнала: 2024, Номер unknown

Опубликована: Дек. 8, 2024

Abstract Accurate soil stratification is essential for geotechnical engineering design. Owing to its effectiveness and efficiency, the cone penetration test (CPT) has been widely applied subsurface stratigraphy, which relies heavily on empiricism correlations type. Recently, deep learning techniques have shown great promise in relationship between CPT data boundaries automatically. However, segmentation of fraught with model measurement uncertainty. This paper introduces an uncertainty‐guided U((‐Net (UGU‐Net) improved boundary segmentation. The UGU‐Net consists three parts: (a) a Bayesian U‐Net predict pixel‐level uncertainty map, (b) reinforcement original labels basis predicted (c) traditional deterministic U‐Net, reinforced final results show that proposed outperforms existing methods terms both high accuracy low A sensitivity study also conducted explore influence key parameters performance. method validated by comparing profile benchmark profiles. code this project available at github.com/Xiaoqi‐Zhou‐suda/UGU‐Net.

Язык: Английский

Процитировано

1
Cyber-risk Perception and Prioritization for Decision-Making and Threat Intelligence DOI Creative Commons
Mario Angelelli, Serena Arima, Christian Catalano

и другие.

arXiv (Cornell University), Год журнала: 2023, Номер unknown

Опубликована: Янв. 1, 2023

Proactive cyber-risk assessment is gaining momentum due to the wide range of sectors that can benefit from prevention cyber-incidents by preserving integrity, confidentiality, and availability data. The rising attention cybersecurity also results increasing connectivity cyber-physical systems, which generates multiple sources uncertainty about emerging cyber-vulnerabilities. This work introduces a robust statistical framework for quantitative qualitative reasoning under cyber-vulnerabilities their prioritisation. Specifically, we take advantage mid-quantile regression deal with ordinal risk assessments, compare it current alternatives ranking graded responses. For this purpose, identify novel accuracy measure suited rank invariance partial knowledge whole set existing vulnerabilities. model tested on both simulated real data selected databases support evaluation, exploitation, or response in realistic contexts. Such datasets allow us models measures, discussing implications threat intelligence decision-making operational scenarios.

Язык: Английский

Процитировано

2
A robust statistical framework for cyber-vulnerability prioritisation under partial information in threat intelligence DOI Creative Commons
Mario Angelelli, Serena Arima, Christian Catalano

и другие.

Expert Systems with Applications, Год журнала: 2024, Номер 255, С. 124572 - 124572

Опубликована: Июнь 25, 2024

Proactive cyber-risk assessment is gaining momentum due to the wide range of sectors that can benefit from prevention cyber-incidents by preserving integrity, confidentiality, and availability data. The rising attention cybersecurity also results increasing connectivity cyber–physical systems, which generates multiple sources uncertainty about emerging cyber-vulnerabilities. This work introduces a robust statistical framework for quantitative qualitative reasoning under cyber-vulnerabilities their prioritisation. Specifically, we take advantage mid-quantile regression deal with ordinal risk assessments, compare it current alternatives ranking graded responses. For this purpose, identify novel accuracy measure suited rank invariance partial knowledge whole set existing vulnerabilities. model tested on both simulated real data selected databases support evaluation, exploitation, or response in realistic contexts. Such datasets allow us models measures, discussing implications threat intelligence decision-making operational scenarios.

Язык: Английский

Процитировано

0