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

Efficient Temporally-Aware DeepFake Detection using H.264 Motion Vectors

Sabine Süsstrunk, Alessio Verardo, Yufan Ren, Peter Arpad Grönquist, Qingyi He

Video DeepFakes are fake media created with Deep Learning (DL) that manipulate a person’s expression or identity. Most current DeepFake detection methods analyze each frame independently, ignoring inconsistencies and unnatural movements between frames. Som ...

2024

Machine learning-aided generative molecular design

Philippe Schwaller, Jeff Guo

Machine learning has provided a means to accelerate early-stage drug discovery by combining molecule generation and filtering steps in a single architecture that leverages the experience and design preferences of medicinal chemists. However, designing mach ...

Nature Portfolio2024

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

Saeed Saadatnejad

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 ...

EPFL2023

Fast Adversarial Training With Adaptive Step Size

Mathieu Salzmann, Sabine Süsstrunk, Jue Wang, Chen Liu, Yong Zhang, Zhuoyi Huang

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 ...

Ieee-Inst Electrical Electronics Engineers Inc2023

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

Jean-Philippe Thiran, Guillaume Marc Georges Vray, Seyedbehzad Bozorgtabar, Devavrat Tomar

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 ...

Los Alamitos2023

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

Seyed Hamed Hassani, Volkan Cevher, Fabian Ricardo Latorre Gomez

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 ...

2023

On the Privacy-Robustness-Utility Trilemma in Distributed Learning

Rachid Guerraoui, John Stephan, Nirupam Gupta, Rafaël Benjamin Pinot, Youssef Allouah

The ubiquity of distributed machine learning (ML) in sensitive public domain applications calls for algorithms that protect data privacy, while being robust to faults and adversarial behaviors. Although privacy and robustness have been extensively studied ...

2023

Robust Training and Verification of Deep Neural Networks

Fabian Ricardo Latorre Gomez

According to the proposed Artificial Intelligence Act by the European Comission (expected to pass at the end of 2023), the class of High-Risk AI Systems (Title III) comprises several important applications of Deep Learning like autonomous driving vehicles ...

EPFL2023

Estimating and Improving the Robustness of Attributions in Text

Ádám Dániel Ivánkay

End-to-end learning methods like deep neural networks have been the driving force in the remarkable progress of machine learning in recent years. However, despite their success, the deployment process of such networks in safety-critical use cases, such as ...

EPFL2023

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

Siyuan Li, Zhuoqian Yang

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 ...

Ieee Computer Soc2023

Machine Learning Security in Industry: A Quantitative Survey

Kathrin Grosse

Despite the large body of academic work on machine learning security, little is known about the occurrence of attacks on machine learning systems in the wild. In this paper, we report on a quantitative study with 139 industrial practitioners. We analyze at ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2023

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

Sébastien Marcel, Christophe René Joseph Ecabert, Parsa Rahimi Noshanagh

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 ...

IEEE2023

Robustness and invariance properties of image classifiers

Apostolos Modas

Deep neural networks have achieved impressive results in many image classification tasks. However, since their performance is usually measured in controlled settings, it is important to ensure that their decisions remain correct when deployed in noisy envi ...

EPFL2022

RG-Flow: a hierarchical and explainable flow model based on renormalization group and sparse prior

Dian Wu

Flow-based generative models have become an important class of unsupervised learning approaches. In this work, we incorporate the key ideas of renormalization group (RG) and sparse prior distribution to design a hierarchical flow-based generative model, RG ...

IOP Publishing Ltd2022

Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks

Chen Liu

In the last decade, deep neural networks have achieved tremendous success in many fields of machine learning. However, they are shown vulnerable against adversarial attacks: well-designed, yet imperceptible, perturbations can make the state-of-the-art deep ...

EPFL2022

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

Francesco La Rosa

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 ...

EPFL2022

Synthetic Disinformation Attacks on Automated Fact Verification Systems

Antoine Bosselut

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 ...

ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE2022

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

Mahsa Shoaran, Bingzhao Zhu

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 ...

IEEE2021

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

Michaël Unser, Laurène Donati, Harshit Gupta, Michael Thompson McCann

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 ...

2021

Optimizing Latent Space Directions For GAN-based Local Image Editing

Sabine Süsstrunk, Ehsan Pajouheshgar, Tong Zhang

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 ...

IEEE2021