Visible to the public Detecting Deepfake Videos using Attribution-Based Confidence Metric

TitleDetecting Deepfake Videos using Attribution-Based Confidence Metric
Publication TypeConference Paper
Year of Publication2020
AuthorsFernandes, Steven, Raj, Sunny, Ewetz, Rickard, Pannu, Jodh Singh, Kumar Jha, Sumit, Ortiz, Eddy, Vintila, Iustina, Salter, Margaret
Conference Name2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Date Publishedjun
Keywordsattribution, composability, Computational modeling, Databases, Face, Human Behavior, machine learning, Measurement, Metrics, pubcrawl, Training data, Videos
AbstractRecent advances in generative adversarial networks have made detecting fake videos a challenging task. In this paper, we propose the application of the state-of-the-art attribution based confidence (ABC) metric for detecting deepfake videos. The ABC metric does not require access to the training data or training the calibration model on the validation data. The ABC metric can be used to draw inferences even when only the trained model is available. Here, we utilize the ABC metric to characterize whether a video is original or fake. The deep learning model is trained only on original videos. The ABC metric uses the trained model to generate confidence values. For, original videos, the confidence values are greater than 0.94.
Citation Keyfernandes_detecting_2020