Por favor, use este identificador para citar o enlazar este ítem: http://hdl.handle.net/10609/152492
Título : Toward universal detector for synthesized images by estimating generative AI models
Autoría: Seo, Ryota
Kuribayashi, Minoru  
Ura, Akinobu
Mallet, Antoine  
Cogranne, Rémi  
Mazurczyk, Wojciech  
Megias, David  
Citación : Seo, R. [Ryota], Kuribayashi, M. [Minoru], Ura, A. [Akinobu], Mallet, A. [Antoine], Cogranne, R. [Rémi], Mazurczyk, W. [Wojciech] & Megías, D. [David].(2024). Toward Universal Detector for Synthesized Images by Estimating Generative AI Models. 2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) (p. 1-6). Piscataway: IEEE
Resumen : One of the vulnerabilities in discriminators for AI-generated images is that the classification accuracy degrades when dealing with images generated using methods other than those they were trained on. As a countermeasure, in this study, we propose an image generation method estimator. The process of discrimination involves the input of an image to the estimator, which estimates the method used for its generation. Subsequently, a specialized fake image discriminator tailored to the estimated image generation method is used to identify the authenticity of the image. The activation functions are also considered according to the estimation results and analyzed for those discriminators. Discrimination scores are weighted and aggregated according to the estimation results, and the final decision is output. Our experimental results showed that the estimator achieved a classification accuracy of approximately 90% for 18 types of AI-generated images. Furthermore, by selecting the top two estimations in order of confidence, the accuracy increased to around 98%.
DOI: https://doi.org/10.1109/APSIPAASC63619.2025.10849267
Tipo de documento: info:eu-repo/semantics/conferenceObject
Versión del documento: info:eu-repo/semantics/acceptedVersion
Fecha de publicación : 27-ene-2025
Aparece en las colecciones: Conferències

Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
Seo_IEEE_Toward.pdf2,69 MBAdobe PDFVista previa
Visualizar/Abrir
Comparte:
Exporta:
Consulta las estadísticas

Los ítems del Repositorio están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.