20.500.12556/RUL-155116 Odkrivanje globokih ponaredkov z video transformerji Deepfake Detection using Video Transformers V diplomski nalogi se soočamo s problematiko odkrivanja lažnih posnetkov. Lažni posnetki se na spletu pojavljajo vse pogosteje in z uporabo tehnologije globokih ponaredkov (angl. Deepfakes) za ustvarjanje teh posnetkov postajajo tudi tako prepričljivi, da lahko pretentajo ljudi. Cilj globokih ponaredkov je velikokrat širjenje dezinformacij ali omadeževanje ugleda znane osebe. Za namen računalniškega prepoznavanja globokih ponaredkov predstavimo dva sorodna pristopa, ki temeljita na arhitekturi transformerjev in delujeta na osnovi posnetka, za razliko od drugih metod, ki delujejo na osnovi posameznih slik. Imenujeta se Video Vision Transformer (ViViT) in UniFormerV2. Modele teh pristopov smo naučili na podatkovnih zbirkah globokih ponaredkov FaceForensics++ in Celeb-DF-v2. Preizkusili smo tudi zmogljivost modelov na testnem naboru iz zbirke DFDC. S temi modeli smo dosegli rezultate, ki so primerljivi tudi z dosedaj najboljšimi na tem področju. V okviru diplomske naloge opišemo še našo metodologijo, tehnologijo uporabljenih modelov in podrobnosti implementacije. Predstavimo tudi podrobne rezultate, eksperimente ter primerjavo z drugačnimi pristopi pri odkrivanju globokih ponaredkov. In this bachelor's thesis we examine the task of Deepfake detection. These fake videos are appearing online with increasing frequency. With the use of deep learning for their creation, they have become convincing enough to trick humans. The goal of creating these fake videos is often to spread misinformation or damage the reputations of celebrities. For this task of detecting fake videos, we present two related video-based approaches, with each using the transformer architecture. These approaches are known as the Video Vision Transformer (ViViT) and UniFormerV2. We trained models of these two approaches on two datasets of fake videos, FaceForensics++ and Celeb-DF-v2. We also tested the performance of these models on an additional test set of videos from the DFDC dataset. With the use of these models, we have achieved results comparable to state-of-the-art approaches in this field. As part of the thesis, we describe our methodology, the technologies used in the approaches, and certain implementation details. We also present detailed results of the models we trained, our experiments, and a comparison of our results with some of the different approaches to Deepfake detection. strojno učenje globoko učenje lažni posnetki globoki ponaredki Video Vision Transformer UniFormerV2 machine learning deep learning Deepfake detection Video Vision Transformer UniFormerV2 true false false Slovenski jezik Angleški jezik Diplomsko delo/naloga 2024-03-20 16:10:01 2024-03-20 16:10:09 2024-03-28 07:50:17 0000-00-00 00:00:00 2024 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 36891 190633987 Logar_Tadej_-_Odkrivanje_globokih_ponaredkov_z_video_transformerji.pdf Logar_Tadej_-_Odkrivanje_globokih_ponaredkov_z_video_transformerji.pdf 1 1990B1994EE9487A5727044C49273AAE 6178d04850a470becaa79fbdfd00a83bb60d8685a3c41b5ee3ef5beb9fea7043 f1a8c290-e6cb-11ee-8d8c-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=181901 Fakulteta za računalništvo in informatiko 0 0 0