A study on vulnerability analysis process of generative AI-based digital medical contents

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F44555601%3A13510%2F25%3A43899387" target="_blank" >RIV/44555601:13510/25:43899387 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S2542660525002720?via%3Dihub" target="_blank" >https://www.sciencedirect.com/science/article/pii/S2542660525002720?via%3Dihub</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.iot.2025.101759" target="_blank" >10.1016/j.iot.2025.101759</a>

Jazyk výsledku

angličtina

Název v původním jazyce

A study on vulnerability analysis process of generative AI-based digital medical contents

Popis výsledku v původním jazyce

This paper conducts a sequential analysis of the security vulnerabilities associated with AI-generated digital medical content across ten key areas and presents strategies to enhance the safety and reliability of medical AI systems. The study comprehensively examines aspects such as the quality and integrity of digital content, risks of privacy exposure, model security vulnerabilities, system security, ethical risks, performance stability, regulatory compliance, interoperability, and disaster recovery capabilities. To evaluate the AI system&apos;s vulnerabilities, quantitative metrics such as Data Accuracy (DA), Personal Information Risk (PIR), and Model Robustness (MR) are utilized. The results underscore the importance of strengthening encryption, improving backup systems, and enhancing defenses against adversarial attacks. These findings highlight the critical need for reinforcing security protocols, adhering to ethical standards, and ensuring strict compliance with international regulations. The study offers vital guidelines for developing secure AI systems that can be effectively integrated into medical applications, contributing to the safe and reliable use of generative AI technology in healthcare settings.

Název v anglickém jazyce

A study on vulnerability analysis process of generative AI-based digital medical contents

Popis výsledku anglicky

This paper conducts a sequential analysis of the security vulnerabilities associated with AI-generated digital medical content across ten key areas and presents strategies to enhance the safety and reliability of medical AI systems. The study comprehensively examines aspects such as the quality and integrity of digital content, risks of privacy exposure, model security vulnerabilities, system security, ethical risks, performance stability, regulatory compliance, interoperability, and disaster recovery capabilities. To evaluate the AI system&apos;s vulnerabilities, quantitative metrics such as Data Accuracy (DA), Personal Information Risk (PIR), and Model Robustness (MR) are utilized. The results underscore the importance of strengthening encryption, improving backup systems, and enhancing defenses against adversarial attacks. These findings highlight the critical need for reinforcing security protocols, adhering to ethical standards, and ensuring strict compliance with international regulations. The study offers vital guidelines for developing secure AI systems that can be effectively integrated into medical applications, contributing to the safe and reliable use of generative AI technology in healthcare settings.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Internet of Things Journal

ISSN

2543-1536

e-ISSN

2542-6605

Svazek periodika

34

Číslo periodika v rámci svazku

November

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

15

Strana od-do

1-15

Kód UT WoS článku

001573322600001

EID výsledku v databázi Scopus

2-s2.0-105015796754