Search Results for author: Cristian Canton Ferrer

Found 20 papers, 7 papers with code

Generating High Fidelity Data from Low-density Regions using Diffusion Models

no code implementations31 Mar 2022 Vikash Sehwag, Caner Hazirbas, Albert Gordo, Firat Ozgenel, Cristian Canton Ferrer

We observe that uniform sampling from diffusion models predominantly samples from high-density regions of the data manifold.

Localized Uncertainty Attacks

no code implementations17 Jun 2021 Ousmane Amadou Dia, Theofanis Karaletsos, Caner Hazirbas, Cristian Canton Ferrer, Ilknur Kaynar Kabul, Erik Meijer

Under this threat model, we create adversarial examples by perturbing only regions in the inputs where a classifier is uncertain.

Adversarial Evaluation of Multimodal Models under Realistic Gray Box Assumption

no code implementations25 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.

General Classification Text Augmentation

Adversarial Threats to DeepFake Detection: A Practical Perspective

no code implementations19 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.

DeepFake Detection Face Swapping +1

Adversarial collision attacks on image hashing functions

no code implementations18 Nov 2020 Brian Dolhansky, Cristian Canton Ferrer

Hashing images with a perceptual algorithm is a common approach to solving duplicate image detection problems.

The DeepFake Detection Challenge (DFDC) Dataset

7 code implementations12 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.

DeepFake Detection Face Swapping

Deep Poisoning: Towards Robust Image Data Sharing against Visual Disclosure

no code implementations14 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.

Face Recognition Image Classification

The Deepfake Detection Challenge (DFDC) Preview Dataset

no code implementations19 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.

DeepFake Detection Face Swapping

Hate Speech in Pixels: Detection of Offensive Memes towards Automatic Moderation

1 code implementation5 Oct 2019 Benet Oriol Sabat, Cristian Canton Ferrer, Xavier Giro-i-Nieto

This work addresses the challenge of hate speech detection in Internet memes, and attempts using visual information to automatically detect hate speech, unlike any previous work of our knowledge.

Hate Speech Detection

Eye In-Painting with Exemplar Generative Adversarial Networks

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).

Towards social pattern characterization in egocentric photo-streams

no code implementations5 Sep 2017 Maedeh Aghaei, Mariella Dimiccoli, Cristian Canton Ferrer, Petia Radeva

Following the increasingly popular trend of social interaction analysis in egocentric vision, this manuscript presents a comprehensive study for automatic social pattern characterization of a wearable photo-camera user, by relying on the visual analysis of egocentric photo-streams.

Time Series

Disentangling Motion, Foreground and Background Features in Videos

1 code implementation13 Jul 2017 Xunyu Lin, Victor Campos, Xavier Giro-i-Nieto, Jordi Torres, Cristian Canton Ferrer

This paper introduces an unsupervised framework to extract semantically rich features for video representation.

Learning by tracking: Siamese CNN for robust target association

no code implementations26 Apr 2016 Laura Leal-Taixé, Cristian Canton Ferrer, Konrad Schindler

This paper introduces a novel approach to the task of data association within the context of pedestrian tracking, by introducing a two-stage learning scheme to match pairs of detections.

Multiple People Tracking Optical Flow Estimation

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