Deepfake

Résumé

vignette|Deepfake sur Kim Jong-Un. Le deepfake , ou hypertrucage, est une technique de synthèse multimédia reposant sur l'intelligence artificielle. Elle peut servir à superposer des fichiers vidéo ou audio existants sur d'autres fichiers vidéo (par exemple changer le visage d'une personne sur une vidéo) ou audio (par exemple reproduire la voix d'une personne pour lui faire dire des choses inventées). Cette technique peut être utilisée pour créer des infox et des canulars malveillants. Le terme deepfake est un mot-valise formé à partir de deep learning (« apprentissage profond ») et de fake (« faux », « contrefait »). Il est possible de créer des hypertrucages en utilisant l'application FakeApp, qui utilise TensorFlow, un outil open source développé par Google. Les hypertrucages vidéos sont aussi appelés infox vidéo ou vidéotox. Histoire Les techniques pour simuler des mouvements faciaux et les transposer sur une personne-cible ont été présentées

Source officielle

https://fr.wikipedia.org/wiki/Deepfake

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Publications associées (6)

Publications associées

Chargement

Personnes associées (1)

Personnes associées

Chargement

Unités associées (1)

Unités associées

Chargement

Concepts associés (10)

Concepts associés

Chargement

Cours associés (2)

Software agents are widely used to control physical, economic and financial processes. The course presents practical methods for implementing software agents and multi-agent systems, supported by programming exercises, and the theoretical underpinnings including computational game theory.

Machine learning and data analysis are becoming increasingly central in many sciences and applications. In this course, fundamental principles and methods of machine learning will be introduced, analyzed and practically implemented.

Cours associés

Chargement

Séances de cours associées (2)

Séances de cours associées

Chargement

, ,

2021

Chargement

Deepfake detection: humans vs. machines

Sébastien Marcel

Deepfake videos, where a person’s face is automatically swapped with a face of someone else, are becoming easier to generate with more realistic results. In response to the threat such manipulations can pose to our trust in video evidence, several large datasets of deepfake videos and many methods to detect them were proposed recently. However, it is still unclear how realistic deepfake videos are for an average person and whether the algorithms are significantly better than humans at detecting them. In this paper, we present a subjective study conducted in a crowdsourcing-like scenario, which systematically evaluates how hard it is for humans to see if the video is deepfake or not. For the evaluation, we used 120 different videos (60 deepfakes and 60 originals) manually pre-selected from the Facebook deepfake database, which was provided in the Kaggle’s Deepfake Detection Challenge 2020. For each video, a simple question: "Is face of the person in the video real of fake?" was answered on average by 19 na ̈ıve subjects. The results of the subjective evaluation were compared with the performance of two different state of the art deepfake detection methods, based on Xception and EfficientNets (B4 variant) neural networks, which were pre- trained on two other large public databases: the Google’s subset from FaceForensics++ and the recent Celeb-DF dataset. The evaluation demonstrates that while the human perception is very different from the perception of a machine, both successfully but in different ways are fooled by deepfakes. Specifically, algorithms struggle to detect those deepfake videos, which human subjects found to be very easy to spot.

Idiap2020

Chargement

DeepFakes: a New Threat to Face Recognition? Assessment and Detection

Sébastien Marcel

It is becoming increasingly easy to automatically replace a face of one person in a video with the face of another person by using a pre-trained generative adversarial network (GAN). Recent public scandals, e.g., the faces of celebrities being swapped onto pornographic videos, call for automated ways to detect these Deepfake videos. To help developing such methods, in this paper, we present the first publicly available set of Deepfake videos generated from videos of VidTIMIT database. We used open source software based on GANs to create the Deepfakes, and we emphasize that training and blending parameters can significantly impact the quality of the resulted videos. To demonstrate this impact, we generated videos with low and high visual quality (320 videos each) using differently tuned parameter sets. We showed that the state of the art face recognition systems based on VGG and Facenet neural networks are vulnerable to Deepfake videos, with 85.62% and 95.00% false acceptance rates respectively, which means methods for detecting Deepfake videos are necessary. By considering several baseline approaches, we found that audio-visual approach based on lip-sync inconsistency detection was not able to distinguish Deepfake videos. The best performing method, which is based on visual quality metrics and is often used in presentation attack detection domain, resulted in 8.97% equal error rate on high quality Deepfakes. Our experiments demonstrate that GAN-generated Deepfake videos are challenging for both face recognition systems and existing detection methods, and the further development of face swapping technology will make it even more so.

Idiap2018

Chargement