Assessment framework for deepfake detection in real-world situations

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.

In recent years, the remarkable progress in facial manipulation techniques has raised social concerns due to their potential malicious usage and has received considerable attention from both industry and academia. While current deep learning-based face for ...

In recent years, new emerging immersive imaging modalities, e.g. light fields, have been receiving growing attention, becoming increasingly widespread over the years. Light fields are often captured through multi-camera arrays or plenoptic cameras, with th ...

We present 3DHumanGAN, a 3D-aware generative adversarial network that synthesizes photo-like images of fullbody humans with consistent appearances under different view-angles and body-poses. To tackle the representational and computational challenges in sy ...

Today's continued increase in demand for processing power, despite the slowdown of Moore's law, has led to an increase in processor count, which has resulted in energy consumption and distribution problems. To address this, there is a growing trend toward ...

Forecasting is a capability inherent in humans when navigating. Humans routinely plan their paths, considering the potential future movements of those around them. Similarly, to achieve comparable sophistication and safety, autonomous systems must embrace ...

Modern data management systems aim to provide both cutting-edge functionality and hardware efficiency. With the advent of AI-driven data processing and the post-Moore Law era, traditional memory-bound scale-up data management operations face scalability ch ...

Recently, it has been exposed that some modern facial recognition systems could discriminate specific demographic groups and may lead to unfair attention with respect to various facial attributes such as gender and origin. The main reason are the biases in ...

We develop an exchange rate target zone model with finite exit time and non-Gaussian tails. We show how the tails are a consequence of time-varying investor risk aversion, which generates mean-preserving spreads in the fundamental distribution. We solve ex ...

Acoustic emission (AE) monitoring is a useful technique to monitor the health of a structure continuously, helping to prevent potential failure. AE are elastic waves produced and emitted during fracture processes inside a material and are recorded by senso ...

Magnetic resonance imaging (MRI) has been a valuable tool in investigating the pathological cascade of Alzheimer's disease (AD) and its progression, which are still open questions. Although some MRI-derived hallmarks in terms of functional connectivity and ...

Recent works have identified a gap between research and practice in artificial intelligence security: threats studied in academia do not always reflect the practical use and security risks of AI. For example, while models are often studied in isolation, th ...

Security system designers favor worst-case security metrics, such as those derived from differential privacy (DP), due to the strong guarantees they provide. On the downside, these guarantees result in a high penalty on the system's performance. In this pa ...

Embedded systems confront two opposite goals: low-power operation and high performance. The current trend to reach these goals is toward heterogeneous platforms, including multi-core architectures with heterogeneous cores and hardware accelerators. The lat ...

Dataflow programming is a methodology that enables the development of high-level, parametric programs that are independent of the underlying platform. This approach is particularly useful for heterogeneous platforms, as it eliminates the need to rewrite ap ...

Risk management has become an essential element in the functioning of modern society. Correct risk identification and assessment are undoubtedly crucial to improving overall safety; nevertheless, often, it is accompanied by the wrong selection of correctiv ...

Ultrafast ultrasound imaging, characterized by high frame rates, generates low-quality images. Convolutional neural networks (CNNs) have demonstrated great potential to enhance image quality without compromising the frame rate. However, CNNs have been most ...

Assessment framework for deepfake detection in real-world situations

Chat with Graph Search

Improving Deepfake Detectors against Real-world Perturbations with Amplitude-Phase Switch Augmentation

Towards learning-based denoising of light fields

3DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mapping

Compilation and Design Space Exploration of Dataflow Programs for Heterogeneous CPU-GPU Platforms

Deep Generative Models for Autonomous Driving: from Motion Forecasting to Realistic Image Synthesis

Post-Moore's Law Fusion: High-Bandwidth Memory, Accelerators, and Native Half-Precision Processing for CPU-Local Analytics

Toward responsible face datasets: modeling the distribution of a disentangled latent space for sampling face images from demographic groups

Can one hear the shape of a target zone?

Automatic and high-precision acoustic emission-based structural health monitoring of concrete structures

Brain microstructural and functional MRI: developments and application to a rat model of Alzheimer's disease

Towards more Practical Threat Models in Artificial Intelligence Security

Bayes Security: A Not So Average Metric

Acceleration of Control Intensive Applications on Coarse-Grained Reconfigurable Arrays for Embedded Systems

Design Space Exploration for Partitioning Dataflow Program on CPU-GPU Heterogeneous System

Safety risk management in University laboratories

A KL Divergence-Based Loss for In Vivo Ultrafast Ultrasound Image Enhancement with Deep Learning