Improving Deepfake Detectors against Real-world Perturbations with Amplitude-Phase Switch Augmentation
Related publications (32)
Graph Chatbot
Chat with Graph Search
Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
The Materials Genome Approach (MGA) aims to accelerate development of new materials by incorporating computational and data-driven approaches to reduce the cost of identification of optimal structures for a given application. Here, we use the MGA to guide ...
With the increasing amount of video being consumed by people daily, there is a danger of the rise in maliciously modified video content (i.e., 'fake news') that could be used to damage innocent people or to impose a certain agenda, e.g., meddle in election ...
The possibility of measuring the gas-phase velocity in a two-phase mixture through the use of neutron noise techniques is demonstrated in the zero-power reactor CROCUS of the Ecole Polytechnique Federale de Lausanne. It is the first step toward the experim ...
It is increasingly easy to automatically swap faces in images and video or morph two faces into one using generative adversarial networks (GANs). The high quality of the resulted deep-morph raises the question of how vulnerable the current face recognition ...
2019
, ,
A large body of research has focused on adversarial attacks which require to modify all input features with small l2- or l∞-norms. In this paper we instead focus on query-efficient sparse attacks in the black-box setting. Our versatile framework, Sparse-RS ...
2020
It is becoming increasingly easy to automatically replace a face of one person in a video with the face of another person by using a pre-trained generative adversarial network (GAN). Recent public scandals, e.g., the faces of celebrities being swapped onto ...
2019
,
Each smile is unique: one person surely smiles in different ways (e.g. closing/opening the eyes or mouth). Given one input image of a neutral face, can we generate multiple smile videos with distinctive characteristics? To tackle this one-to-many video gen ...
IEEE2018
It is becoming increasingly easy to automatically replace a face of one person in a video with the face of another person by using a pre-trained generative adversarial network (GAN). Recent public scandals, e.g., the faces of celebrities being swapped onto ...
Idiap2018
In this study, we apply interferometric microscopy to study the phase, alongside the intensity, of the light field transmitted through a wide variety of samples. Additionally, we conduct those interferometric measurements at different wavelengths within th ...
Pd nanoparticles (NPs) with a small size and narrow size distribution were prepared from the decomposition of Pd(OAc)(2) in a series of hydroxyl-functionalized ionic liquids (ILs) comprising the 1-(2'-hydroxylethyl)-3-methylimidazolium cation and various a ...