Enregistré dans:
Détails bibliographiques
Auteurs principaux: Simpson, Lachlan, Costanza, Federico, Millar, Kyle, Cheng, Adriel, Lim, Cheng-Chew, Chew, Hong Gunn
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2407.16233
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913708956975104
author Simpson, Lachlan
Costanza, Federico
Millar, Kyle
Cheng, Adriel
Lim, Cheng-Chew
Chew, Hong Gunn
author_facet Simpson, Lachlan
Costanza, Federico
Millar, Kyle
Cheng, Adriel
Lim, Cheng-Chew
Chew, Hong Gunn
contents Adversarial attacks on explainability models have drastic consequences when explanations are used to understand the reasoning of neural networks in safety critical systems. Path methods are one such class of attribution methods susceptible to adversarial attacks. Adversarial learning is typically phrased as a constrained optimisation problem. In this work, we propose algebraic adversarial examples and study the conditions under which one can generate adversarial examples for integrated gradients. Algebraic adversarial examples provide a mathematically tractable approach to adversarial examples.
format Preprint
id arxiv_https___arxiv_org_abs_2407_16233
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Algebraic Adversarial Attacks on Integrated Gradients
Simpson, Lachlan
Costanza, Federico
Millar, Kyle
Cheng, Adriel
Lim, Cheng-Chew
Chew, Hong Gunn
Machine Learning
Group Theory
Adversarial attacks on explainability models have drastic consequences when explanations are used to understand the reasoning of neural networks in safety critical systems. Path methods are one such class of attribution methods susceptible to adversarial attacks. Adversarial learning is typically phrased as a constrained optimisation problem. In this work, we propose algebraic adversarial examples and study the conditions under which one can generate adversarial examples for integrated gradients. Algebraic adversarial examples provide a mathematically tractable approach to adversarial examples.
title Algebraic Adversarial Attacks on Integrated Gradients
topic Machine Learning
Group Theory
url https://arxiv.org/abs/2407.16233