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

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

Improved calorimetric particle identification in NA62 using machine learning techniques

Alessandro Mapelli, Radoslav Marchevski, Alina Kleimenova

Measurement of the ultra-rare K+ -> pi(+)nu(nu) over bar over bar decay at the NA62 experiment at CERN requires high-performance particle identification to distinguish muons from pions. Calorimetric identification currently in use, based on a boosted decis ...

New York2023

Accelerated deep self-supervised ptycho-laminography for three-dimensional nanoscale imaging of integrated circuits

Yi Jiang, Manuel Guizar Sicairos

Three-dimensional inspection of nanostructures such as integrated circuits is important for security and reliability assurance. Two scanning operations are required: ptychographic to recover the complex transmissivity of the specimen, and rotation of the s ...

2023

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

On the robustness of randomized classifiers to adversarial examples

Rafaël Benjamin Pinot

This paper investigates the theory of robustness against adversarial attacks. We focus on randomized classifiers (i.e. classifiers that output random variables) and provide a thorough analysis of their behavior through the lens of statistical learning theo ...

SPRINGER2022

Predicting in Uncertain Environments: Methods for Robust Machine Learning

Paul Thierry Yves Rolland

One of the main goal of Artificial Intelligence is to develop models capable of providing valuable predictions in real-world environments. In particular, Machine Learning (ML) seeks to design such models by learning from examples coming from this same envi ...

EPFL2022

Understanding Deep Neural Networks using Adversarial Attacks

Krishna Kanth Nakka

Deep Neural Networks (DNNs) have achieved great success in a wide range of applications, such as image recognition, object detection, and semantic segmentation. Even thoughthe discriminative power of DNNs is nowadays unquestionable, serious concerns have a ...

EPFL2022

Stop Wasting my FLOPS: Improving the Efficiency of Deep Learning Models

Angelos Katharopoulos

Deep neural networks have completely revolutionized the field of machinelearning by achieving state-of-the-art results on various tasks ranging fromcomputer vision to protein folding. However, their application is hindered bytheir large computational and m ...

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

Adversarial training with informed data selection

Pascal Frossard, Javier Alejandro Maroto Morales, Marcele Oliveira Kuhfuss de Mendonça

With the increasing amount of available data and advances in computing capabilities, deep neural networks (DNNs) have been successfully employed to solve challenging tasks in various areas, including healthcare, climate, and finance. Nevertheless, state-of ...

IEEE2022

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

Graph Chatbot

Chat with Graph Search

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

Improved calorimetric particle identification in NA62 using machine learning techniques

Accelerated deep self-supervised ptycho-laminography for three-dimensional nanoscale imaging of integrated circuits

Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks.

On the robustness of randomized classifiers to adversarial examples

Predicting in Uncertain Environments: Methods for Robust Machine Learning

Understanding Deep Neural Networks using Adversarial Attacks

Stop Wasting my FLOPS: Improving the Efficiency of Deep Learning Models

Essays in Empirical Asset Pricing

Adversarial training with informed data selection

Stop Wasting my FLOPS: Improving the Efficiency of Deep Learning Models

Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks.

On the robustness of randomized classifiers to adversarial examples

Adversarial training with informed data selection

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

Accelerated deep self-supervised ptycho-laminography for three-dimensional nanoscale imaging of integrated circuits

Improved calorimetric particle identification in NA62 using machine learning techniques

Predicting in Uncertain Environments: Methods for Robust Machine Learning

Understanding Deep Neural Networks using Adversarial Attacks

Essays in Empirical Asset Pricing