Search Results for author: Pavel Korshunov

Found 8 papers, 4 papers with code

Vulnerability of Automatic Identity Recognition to Audio-Visual Deepfakes

no code implementations29 Nov 2023 Pavel Korshunov, Haolin Chen, Philip N. Garner, Sebastien Marcel

From the publicly available speech dataset LibriTTS, we also created a separate database of only audio deepfakes LibriTTS-DF using several latest text to speech methods: YourTTS, Adaspeech, and TorToiSe.

Face Recognition Face Swapping +2

Are GAN-based Morphs Threatening Face Recognition?

1 code implementation5 May 2022 Eklavya Sarkar, Pavel Korshunov, Laurent Colbois, Sébastien Marcel

Morphing attacks are a threat to biometric systems where the biometric reference in an identity document can be altered.

Face Recognition Image Morphing

Deepfake detection: humans vs. machines

no code implementations7 Sep 2020 Pavel Korshunov, Sébastien Marcel

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.

DeepFake Detection Face Swapping

Vulnerability of Face Recognition to Deep Morphing

no code implementations3 Oct 2019 Pavel Korshunov, Sébastien Marcel

We show that the state of the art face recognition systems based on VGG and Facenet neural networks are vulnerable to the deep morph videos, with 85. 62 and 95. 00 false acceptance rates, respectively, which means methods for detecting these videos are necessary.

Face Recognition Face Swapping +1

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

1 code implementation20 Dec 2018 Pavel Korshunov, Sebastien Marcel

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.

Constrained Lip-synchronization Face Recognition +2

Cannot find the paper you are looking for? You can Submit a new open access paper.