Detecting Deepfakes with Metric Learning

by   Akash Kumar, et al.
IIT Mandi
Delhi Technological University

With the arrival of several face-swapping applications such as FaceApp, SnapChat, MixBooth, FaceBlender and many more, the authenticity of digital media content is hanging on a very loose thread. On social media platforms, videos are widely circulated often at a high compression factor. In this work, we analyze several deep learning approaches in the context of deepfakes classification in high compression scenario and demonstrate that a proposed approach based on metric learning can be very effective in performing such a classification. Using less number of frames per video to assess its realism, the metric learning approach using a triplet network architecture proves to be fruitful. It learns to enhance the feature space distance between the cluster of real and fake videos embedding vectors. We validated our approaches on two datasets to analyze the behavior in different environments. We achieved a state-of-the-art AUC score of 99.2 90.71 especially helpful on social media platforms where data compression is inevitable.


page 1

page 3

page 4


Learning Double-Compression Video Fingerprints Left from Social-Media Platforms

Social media and messaging apps have become major communication platform...

Learning Invariant Representations of Social Media Users

The evolution of social media users' behavior over time complicates user...

Metric Learning for Anti-Compression Facial Forgery Detection

Detecting facial forgery images and videos is an increasingly important ...

Mixup-based Deep Metric Learning Approaches for Incomplete Supervision

Deep learning architectures have achieved promising results in different...

Road Network Metric Learning for Estimated Time of Arrival

Recently, deep learning have achieved promising results in Estimated Tim...

Hashing and metric learning for charged particle tracking

We propose a novel approach to charged particle tracking at high intensi...

Sentimental LIAR: Extended Corpus and Deep Learning Models for Fake Claim Classification

The rampant integration of social media in our every day lives and cultu...

Code Repositories


Deepfakes Video classification via CNN, LSTM, C3D and triplets

view repo

Please sign up or login with your details

Forgot password? Click here to reset