no code implementations • 6 Apr 2021 • Caner Hazirbas, Joanna Bitton, Brian Dolhansky, Jacqueline Pan, Albert Gordo, Cristian Canton Ferrer
The videos were recorded in multiple U. S. states with a diverse set of adults in various age, gender and apparent skin tone groups.
no code implementations • 25 Nov 2020 • Ivan Evtimov, Russel Howes, Brian Dolhansky, Hamed Firooz, Cristian Canton Ferrer
This work examines the vulnerability of multimodal (image + text) models to adversarial threats similar to those discussed in previous literature on unimodal (image- or text-only) models.
no code implementations • 19 Nov 2020 • Paarth Neekhara, Brian Dolhansky, Joanna Bitton, Cristian Canton Ferrer
We perform our evaluations on the winning entries of the DeepFake Detection Challenge (DFDC) and demonstrate that they can be easily bypassed in a practical attack scenario by designing transferable and accessible adversarial attacks.
no code implementations • 18 Nov 2020 • Brian Dolhansky, Cristian Canton Ferrer
Hashing images with a perceptual algorithm is a common approach to solving duplicate image detection problems.
8 code implementations • 12 Jun 2020 • Brian Dolhansky, Joanna Bitton, Ben Pflaum, Jikuo Lu, Russ Howes, Menglin Wang, Cristian Canton Ferrer
In addition to Deepfakes, a variety of GAN-based face swapping methods have also been published with accompanying code.
no code implementations • 14 Dec 2019 • Hao Guo, Brian Dolhansky, Eric Hsin, Phong Dinh, Cristian Canton Ferrer, Song Wang
Due to respectively limited training data, different entities addressing the same vision task based on certain sensitive images may not train a robust deep network.
no code implementations • 19 Oct 2019 • Brian Dolhansky, Russ Howes, Ben Pflaum, Nicole Baram, Cristian Canton Ferrer
In this paper, we introduce a preview of the Deepfakes Detection Challenge (DFDC) dataset consisting of 5K videos featuring two facial modification algorithms.
2 code implementations • CVPR 2018 • Brian Dolhansky, Cristian Canton Ferrer
This paper introduces a novel approach to in-painting where the identity of the object to remove or change is preserved and accounted for at inference time: Exemplar GANs (ExGANs).