Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks

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.

Multiple sclerosis (MS) is the most common demyelinating disease of the central nervous system and affects almost 3 million people worldwide. There is currently no cure for MS, and its symptoms, starting with fatigue and weakness, often progress over time ...

The Joint Photographic Experts Group (JPEG) AI learning-based image coding system is an ongoing joint standardization effort between International Organization for Standardization (ISO), International Electrotechnical Commission (IEC), and International Te ...

Automated fact-checking is a needed technology to curtail the spread of online misinformation. One current framework for such solutions proposes to verify claims by retrieving supporting or refuting evidence from related textual sources. However, the reali ...

Modern machine learning tools have shown promise in detecting symptoms of neurological disorders. However, current approaches typically train a unique classifier for each subject. This subject-specific training scheme requires long labeled recordings from ...

A large body of work shows that machine learning (ML) models can leak sensitive or confidential information about their training data. Recently, leakage due to distribution inference (or property inference) attacks is gaining attention. In this attack, the ...

We present CryoGAN, a new paradigm for single-particle cryo-electron microscopy (cryo-EM) reconstruction based on unsupervised deep adversarial learning. In single-particle cryo-EM, the structure of a biomolecule needs to be reconstructed from a large set ...

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 ...

Generative Adversarial Network (GAN) based localized image editing can suffer from ambiguity between semantic attributes. We thus present a novel objective function to evaluate the locality of an image edit. By introducing the supervision from a pre-traine ...

While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet. The key idea of recent works to ...

The vulnerability of deep neural networks to adversarial attacks has posed significant threats to real-world applications, especially security-critical ones. Given a well-trained model, slight modifications to the input samples can cause drastic changes in ...

Most recent test-time adaptation methods focus on only classification tasks, use specialized network architectures, destroy model calibration or rely on lightweight information from the source domain. To tackle these issues, this paper proposes a novel Tes ...

Nowadays, image and video are the data types that consume most of the resources of modern communication channels, both in fixed and wireless networks. Thus, it is vital to compress visual data as much as possible, while maintaining some target quality leve ...

Chat Generative Pre-trained Transformer (ChatGPT) is currently a trending topic worldwide triggering extensive debate about its predictive power, its potential uses, and its wider implications. Recent publications have demonstrated that ChatGPT can correct ...

Existing approaches to distribute Generative Adversarial Networks (GANs) either (i) fail to scale for they typically put the two components of a GAN (the generator and the discriminator) on different machines, inducing significant communication overhead, o ...

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 ...

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 ...

In learning from demonstrations, many generative models of trajectories make simplifying assumptions of independence. Correctness is sacrificed in the name of tractability and speed of the learning phase. The ignored dependencies, which are often the kinem ...

Limited availability of representative time-to-failure (TTF) trajectories either limits the performance of deep learning (DL)-based approaches on remaining useful life (RUL) prediction in practice or even precludes their application. Generating synthetic d ...

Most state-of-the-art approaches to road extraction from aerial images rely on a CNN trained to label road pixels as foreground and remainder of the image as background. The CNN is usually trained by minimizing pixel-wise losses, which is less than ideal t ...

One prominent approach toward resolving the adversarial vulnerability of deep neural networks is the two-player zero-sum paradigm of adversarial training, in which predictors are trained against adversarially-chosen perturbations of data. Despite the promi ...

Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks

Chat with Graph Search

Deep learning-based analysis of multiple sclerosis lesions with high and ultra-high field MRI

The JPEG AI Standard: Providing Efficient Human and Machine Visual Data Consumption

Synthetic Disinformation Attacks on Automated Fact Verification Systems

Unsupervised Domain Adaptation for Cross-Subject Few-Shot Neurological Symptom Detection

Distribution Inference Risks: Identifying and Mitigating Sources of Leakage

CryoGAN: A New Reconstruction Paradigm for Single-Particle Cryo-EM Via Deep Adversarial Learning

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

Optimizing Latent Space Directions For GAN-based Local Image Editing

Fast Adversarial Training With Adaptive Step Size

Watermarking-based Defense against Adversarial Attacks on Deep Neural Networks

TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation

Learning-based Image Coding: Early Solutions Reviewing and Subjective Quality Evaluation

ChatGPT takes on the European Exam in Core Cardiology: an artificial intelligence success story?

FeGAN: Scaling Distributed GANs

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

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

Generative adversarial training of product of policies for robust and adaptive movement primitives

Controlled physics-informed data generation for deep learning-based remaining useful life prediction under unseen operation conditions

TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation

Adversarial Training Should Be Cast As a Non-Zero-Sum Game