Detecting and attributing ai-generated images with machine learning

The exponential growth of artificial intelligence (AI) usage for image creation emphasizes the urgent necessity for reliable mechanisms to differentiate real photographs from AI-generated counterparts. This thesis will explore the training of various machine-learning systems capable of identifying s...

Full description

Bibliographic Details
Author: Bernabeu Pérez, Pablo
Format: master thesis
Publication Date:2024
Country:España
Institution:Universitat Politècnica de Catalunya (UPC)
Repository:UPCommons. Portal del coneixement obert de la UPC
Language:English
OAI Identifier:oai:upcommons.upc.edu:2117/411626
Online Access:https://hdl.handle.net/2117/411626
Access Level:Open access
Keyword:Artificial intelligence
Machine learning
detecció d'imatges sintètiques
reconeiximent d'imatges sintètiques
models de difusió
ia generativa
synthetic image detection
synthetic image recognition
diffusion models
generative ai
Intel·ligència artificial
Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
Description
Summary:The exponential growth of artificial intelligence (AI) usage for image creation emphasizes the urgent necessity for reliable mechanisms to differentiate real photographs from AI-generated counterparts. This thesis will explore the training of various machine-learning systems capable of identifying synthetic images and determining the generative model responsible for their creation, helping to verify the authenticity and trustworthiness of digital media.