Publication

Sparse Attacks for Manipulating Explanations in Deep Neural Network Models

Related publications (33)

Graph Chatbot

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.

Deep Learning Generalization with Limited and Noisy Labels

Mahsa Forouzesh

Deep neural networks have become ubiquitous in today's technological landscape, finding their way in a vast array of applications. Deep supervised learning, which relies on large labeled datasets, has been particularly successful in areas such as image cla ...

EPFL2023

Leveraging Unlabeled Data to Track Memorization

Patrick Thiran, Mahsa Forouzesh, Hanie Sedghi

Deep neural networks may easily memorize noisy labels present in real-world data, which degrades their ability to generalize. It is therefore important to track and evaluate the robustness of models against noisy label memorization. We propose a metric, ca ...

2023

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

Fundamental Limits in Statistical Learning Problems: Block Models and Neural Networks

Elisabetta Cornacchia

This thesis focuses on two selected learning problems: 1) statistical inference on graphs models, and, 2) gradient descent on neural networks, with the common objective of defining and analysing the measures that characterize the fundamental limits.In the ...

EPFL2023

BLACK-BOX ATTACKS ON IMAGE ACTIVITY PREDICTION AND ITS NATURAL LANGUAGE EXPLANATIONS

Andrea Cavallaro

Explainable AI (XAI) methods aim to describe the decision process of deep neural networks. Early XAI methods produced visual explanations, whereas more recent techniques generate multimodal explanations that include textual information and visual represent ...

Los Alamitos2023

Topologically Better Delineation of Curvilinear Structures

Doruk Oner

Curvilinear structures are frequently observed in a variety of domains and are essential for comprehending neural circuits, detecting fractures in materials, and determining road and irrigation canal networks. It can be costly and time-consuming to manuall ...

EPFL2023

DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applications

Pascal Frossard, Ádám Dániel Ivánkay

Along with the successful deployment of deep neural networks in several application domains, the need to unravel the black-box nature of these networks has seen a significant increase recently. Several methods have been introduced to provide insight into t ...

Assoc Computational Linguistics-Acl2023

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

On Smoothed Explanations: Quality and Robustness

Pascal Frossard, Seyed Mohsen Moosavi Dezfooli, Michail Vlachos, Ahmad Ajalloeian

Explanation methods highlight the importance of the input features in taking a predictive decision, and represent a solution to increase the transparency and trustworthiness in machine learning and deep neural networks (DNNs). However, explanation methods ...

New York2022

Autoencoders reloaded

Hervé Bourlard, Selen Hande Kabil

In Bourlard and Kamp (Biol Cybern 59(4):291-294, 1998), it was theoretically proven that autoencoders (AE) with single hidden layer (previously called "auto-associative multilayer perceptrons") were, in the best case, implementing singular value decomposit ...

SPRINGER2022