Comprehensive AI-Driven Privacy Risk Assessment in Mobile Apps and Social Networks

Blanco Aza, Daniel; Robles Gómez, Antonio; Pastor Vargas, Rafael; Tobarra Abad, María de los Llanos; Vidal Balboa, Pedro; Méndez-Suárez, Mariano

Publicación:
Comprehensive AI-Driven Privacy Risk Assessment in Mobile Apps and Social Networks

dc.contributor.author	Blanco Aza, Daniel
dc.contributor.author	Robles Gómez, Antonio
dc.contributor.author	Pastor Vargas, Rafael
dc.contributor.author	Tobarra Abad, María de los Llanos
dc.contributor.author	Vidal Balboa, Pedro
dc.contributor.author	Méndez-Suárez, Mariano
dc.date.accessioned	2025-07-03T09:44:10Z
dc.date.available	2025-07-03T09:44:10Z
dc.date.issued	2024-01
dc.description	Este artículo ha sido aceptado para su publicación en Cluster Computing, The Journal of Networks, Software Tools and Applications, Springer (JCR 2024: Q1). This article has been accepted for publication in Cluster Computing, The Journal of Networks, Software Tools and Applications, Springer (JCR 2024: Q1)
dc.description.abstract	The pervasive use of mobile applications and social networks has intensified privacy concerns due to the widespread collection, processing, and sharing of personal data. To address these challenges, we introduce SafeMountain, a novel AI-driven framework designed to systematically quantify, evaluate, and visualize privacy risks in mobile apps and social platforms, ensuring strict compliance with international regulations, particularly the General Data Protection Regulation (GDPR). SafeMountain combines static and dynamic code analyses to scrutinize real-world data handling practices and detect potential privacy breaches. It also employs advanced Natural Language Processing (NLP) techniques for automated interpretation and evaluation of privacy policies and Terms of Service. By mapping textual policy disclosures to actual app permissions and behaviors, it identifies discrepancies and highlights potential non-compliance and data misuse. The framework introduces an objective risk scoring mechanism aligned with international standards and regulatory requirements, offering a structured methodology to classify and visualize privacy risks. This risk assessment spans multiple dimensions (predictability, manageability, and disassociability) leveraging privacy engineering principles and regulatory risk factors, and uses an intuitive traffic-light system (Green, Yellow, Red) to enhance transparency and user comprehension. SafeMountain addresses major research gaps, notably the absence of standardized privacy risk scoring and comprehensive visualization tools. By delivering actionable insights into permission consistency, policy transparency, compliance gaps, and data leakage vulnerabilities, it empowers users, developers, and organizations to manage privacy risks proactively. Ultimately, SafeMountain fosters trust through more transparent and accountable data privacy practices across digital ecosystems.	en
dc.description.version	versión final
dc.identifier.citation	Daniel Blanco-Aza, Antonio Robles-Gómez, Rafael Pastor-Vargas, Llanos Tobarra, Pedro Vidal-Balboa, Mariano Méndez-Suárez Cluster Computing, The Journal of Networks, Software Tools and Applications, Springer (JCR 2024: Q1)
dc.identifier.issn	1386-7857; e-ISSN: 1573-7543
dc.identifier.uri	https://hdl.handle.net/20.500.14468/26988
dc.journal.title	Cluster Computing, The Journal of Networks, Software Tools and Applications
dc.language.iso	en
dc.publisher	Springer
dc.relation.center	E.T.S. de Ingeniería Informática
dc.relation.department	Sistemas De Comunicación y Control
dc.rights	info:eu-repo/semantics/openAccess
dc.rights.uri	Atribución-NoComercial-SinDerivadas 4.0 Internacional
dc.subject	12 Matemáticas::1203 Ciencia de los ordenadores ::1203.17 Informática
dc.subject.keywords	SafeMountain	en
dc.subject.keywords	Automated Privacy Risk	en
dc.subject.keywords	Mobile Apps	en
dc.subject.keywords	AI Techniques	en
dc.subject.keywords	PRISMA Methodology	en
dc.subject.keywords	Data Privacy	en
dc.subject.keywords	Privacy Risk Framework	en
dc.subject.keywords	Social Networks Privacy	en
dc.title	Comprehensive AI-Driven Privacy Risk Assessment in Mobile Apps and Social Networks	en
dc.type	artículo	es
dc.type	journal article	en
dspace.entity.type	Publication
relation.isAuthorOfPublication	17556659-f434-4220-841d-aac35f492e62
relation.isAuthorOfPublication	f93103de-336d-47ac-886b-e2cbd425ed87
relation.isAuthorOfPublication	b584f8a3-eb01-4a43-9ed7-5075b74224ae
relation.isAuthorOfPublication.latestForDiscovery	17556659-f434-4220-841d-aac35f492e62