ID-Reveal: Identity-aware DeepFake Video Detection

12/04/2020
by   Davide Cozzolino, et al.
0

State-of-the-art DeepFake forgery detectors are trained in a supervised fashion to answer the question 'is this video real or fake?'. Given that their training is typically method-specific, these approaches show poor generalization across different types of facial manipulations, e.g., face swapping or facial reenactment. In this work, we look at the problem from a different perspective by focusing on the facial characteristics of a specific identity; i.e., we want to answer the question 'Is this the person who is claimed to be?'. To this end, we introduce ID-Reveal, a new approach that learns temporal facial features, specific of how each person moves while talking, by means of metric learning coupled with an adversarial training strategy. Our method is independent of the specific type of manipulation since it is trained only on real videos. Moreover, relying on high-level semantic features, it is robust to widespread and disruptive forms of post-processing. We performed a thorough experimental analysis on several publicly available benchmarks, such as FaceForensics++, Google's DFD, and Celeb-DF. Compared to state of the art, our method improves generalization and is more robust to low-quality videos, that are usually spread over social networks. In particular, we obtain an average improvement of more than 15 accuracy for facial reenactment on high compressed videos.

READ FULL TEXT

page 2

page 4

page 6

page 11

research
03/30/2023

Diff-ID: An Explainable Identity Difference Quantification Framework for DeepFake Detection

Despite the fact that DeepFake forgery detection algorithms have achieve...
research
04/06/2022

Audio-Visual Person-of-Interest DeepFake Detection

Face manipulation technology is advancing very rapidly, and new methods ...
research
08/03/2023

MFIM: Megapixel Facial Identity Manipulation

Face swapping is a task that changes a facial identity of a given image ...
research
11/15/2022

Towards an objective characterization of an individual's facial movements using Self-Supervised Person-Specific-Models

Disentangling facial movements from other facial characteristics, partic...
research
03/15/2021

Metric Learning for Anti-Compression Facial Forgery Detection

Detecting facial forgery images and videos is an increasingly important ...
research
01/18/2022

Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection

One of the most pressing challenges for the detection of face-manipulate...
research
12/21/2021

Watch Those Words: Video Falsification Detection Using Word-Conditioned Facial Motion

In today's era of digital misinformation, we are increasingly faced with...

Please sign up or login with your details

Forgot password? Click here to reset