Publications related to Geometry of adversarial robustness of deep networks: methods and applications

Confidence Matters: Applications to Semantic Segmentation

The successes of deep learning for semantic segmentation can in be, in part, attributed to its scale: a notion that encapsulates the largeness of these computational architectures and the labeled datasets they are trained on. These resource requirements hi ...

EPFL2023

Rethinking data augmentation for adversarial robustness

Kathrin Grosse

Recent work has proposed novel data augmentation methods to improve the adversarial robustness of deep neural networks. In this paper, we re-evaluate such methods through the lens of different metrics that characterize the augmented manifold, finding contr ...

2023

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

Jean-Philippe Thiran, Guillaume Marc Georges Vray, 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 ...

IEEE2023

Continuous-variable neural network quantum states and the quantum rotor model

Giuseppe Carleo

We initiate the study of neural network quantum state algorithms for analyzing continuous-variable quantum systems in which the quantum degrees of freedom correspond to coordinates on a smooth manifold. A simple family of continuous-variable trial wavefunc ...

SPRINGERNATURE2023

Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks

Sabine Süsstrunk, Mathieu Salzmann, Yulun Jiang, Chen Liu, Zhuoyi Huang

We address the problem of stably and efficiently training a deep neural network robust to adversarial perturbations bounded by an

l_1

norm. We demonstrate that achieving robustness against

l_1

-bounded perturbations is more challenging than in the

l_2

...

2023

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

Stereo Confidence Estimation via Locally Adaptive Fusion and Knowledge Distillation

Pascal Frossard, Seungryong Kim

Stereo confidence estimation aims to estimate the reliability of the estimated disparity by stereo matching. Different from the previous methods that exploit the limited input modality, we present a novel method that estimates confidence map of an initial ...

IEEE COMPUTER SOC2023

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

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

Essays in Empirical Asset Pricing

Alexis Arilès Marchal

This thesis consists of three applications of machine learning techniques to empirical asset pricing.In the first part, which is co-authored work with Oksana Bashchenko, we develop a new method that detects jumps nonparametrically in financial time series ...

EPFL2022

Geometry of adversarial robustness of deep networks: methods and applications

Graph Chatbot

Chat with Graph Search

Confidence Matters: Applications to Semantic Segmentation

Rethinking data augmentation for adversarial robustness

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

Continuous-variable neural network quantum states and the quantum rotor model

Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks

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

Stereo Confidence Estimation via Locally Adaptive Fusion and Knowledge Distillation

Robustness and invariance properties of image classifiers

Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks.

Essays in Empirical Asset Pricing

Rethinking data augmentation for adversarial robustness

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

Continuous-variable neural network quantum states and the quantum rotor model

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

Robustness and invariance properties of image classifiers

Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks.

Confidence Matters: Applications to Semantic Segmentation

Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks

Essays in Empirical Asset Pricing

Stereo Confidence Estimation via Locally Adaptive Fusion and Knowledge Distillation