Concept

Abduction (logique)

Publications associées (77)

To Infinity, and Beyond (Coverage)

The pursuit of software security and reliability hinges on the identification and elimination of software vulnerabilities, a challenge compounded by the vast and evolving complexity of modern systems. Fuzzing has emerged as an indispensable technique for b ...

EPFL2024

Monotonicity Reasoning in the Age of Neural Foundation Models

Zeming Chen, Qiyue Gao

The recent advance of large language models (LLMs) demonstrates that these large-scale foundation models achieve remarkable capabilities across a wide range of language tasks and domains. The success of the statistical learning approach challenges our unde ...

Dordrecht2023

Exploiting Explanations to Detect Misclassifications of Deep Learning Models in Power Grid Visual Inspection

Olga Fink, Giovanni Floreale

In the context of automatic visual inspection of infrastructures by drones, Deep Learning (DL) models are used to automatically process images for fault diagnostics. While explainable Artificial Intelligence (AI) algorithms can provide explanations to asse ...

Research Publishing2023

Distribution Inference Risks: Identifying and Mitigating Sources of Leakage

Robert West, Maxime Jean Julien Peyrard, Valentin Hartmann, Léo Nicolas René Meynent

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 ...

IEEE COMPUTER SOC2023

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

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

Specific Gestalt principles cannot explain (un)crowding

Michael Herzog, Oh-Hyeon Choung, Einat Rashal

The standard physiological model has serious problems accounting for many aspects of vision, particularly when stimulus configurations become slightly more complex than the ones classically used, e.g., configurations of Gabors rather than only one or a few ...

FRONTIERS MEDIA SA2023

Sparse Attacks for Manipulating Explanations in Deep Neural Network Models

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

We investigate methods for manipulating classifier explanations while keeping the predictions unchanged. Our focus is on using a sparse attack, which seeks to alter only a minimal number of input features. We present an efficient and novel algorithm for co ...

Los Alamitos2023

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

Space Oddity? A Statistical Formulation of Conjunction Assessment

Anthony Christopher Davison, Soumaya Elkantassi

Satellite conjunctions involving "near misses" of space objects are becoming increasingly likely. One approach to risk analysis for them involves the computation of the collision probability, but this has been regarded as having some counterintuitive prope ...

AMER INST AERONAUTICS ASTRONAUTICS2022

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Connectez-vous pour utiliser Chat avec Graph Search