Ενίσχυση της επιχειρησιακής συνέχειας και της οργανωσιακής ανθεκτικότητας μέσω τοπικών μεγάλων γλωσσικών μοντέλων
View/
Keywords
Επιχειρησιακή συνέχεια ; Τεχνητή νοημοσύνη ; Αρχιτεκτονική RAG ; Κυβερνοασφάλεια ; Διαχείριση κρίσεων ; Business continuity ; Artificial Intelligence ; Local large language models ; Cybersecurity ; Crisis managementAbstract
This thesis explores the convergence of Business Continuity Management and Artificial Intelligence, aiming to enhance organizational resilience through innovative technological solutions. Initially, it provides a comprehensive theoretical analysis of ISO 22301 and ISO/IEC 27001 international standards, focusing on the PDCA cycle and the Business Impact Analysis (BIA) methodology as foundations for effective governance. Subsequently, the study practically investigates the feasibility of utilizing a Local Large Language Model (Local LLM), specifically Mistral 7B, as a compliance advisor within an SME environment, while ensuring data privacy through offline execution. Through the implementation of a Retrieval-Augmented Generation (RAG) architecture and the simulation of a Ransomware attack scenario, the research demonstrates that AI can accurately retrieve security policies and support decision-making processes, provided that it is supported by robust prompt engineering and maintained under human oversight to mitigate inherent technical limitations.
Postgraduate Studies Programme
Κυβερνοασφάλεια και Τεχνολογίες Τεχνητής Νοημοσύνης / MSc Cybersecurity & AI TechnologiesDepartment
Σχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα Ψηφιακών ΣυστημάτωνNumber of pages
60Language
GreekCollections
Except where otherwise noted, this item's license is described as
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα