Enregistré dans:
Détails bibliographiques
Auteurs principaux: Bajcsy, Peter, Bros, Maxime
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2405.13217
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910455328407552
author Bajcsy, Peter
Bros, Maxime
author_facet Bajcsy, Peter
Bros, Maxime
contents This work addresses the problem of planting and defending cryptographic-based backdoors in artificial intelligence (AI) models. The motivation comes from our lack of understanding and the implications of using cryptographic techniques for planting undetectable backdoors under theoretical assumptions in the large AI model systems deployed in practice. Our approach is based on designing a web-based simulation playground that enables planting, activating, and defending cryptographic backdoors in neural networks (NN). Simulations of planting and activating backdoors are enabled for two scenarios: in the extension of NN model architecture to support digital signature verification and in the modified architectural block for non-linear operators. Simulations of backdoor defense against backdoors are available based on proximity analysis and provide a playground for a game of planting and defending against backdoors. The simulations are available at https://pages.nist.gov/nn-calculator
format Preprint
id arxiv_https___arxiv_org_abs_2405_13217
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Interactive Simulations of Backdoors in Neural Networks
Bajcsy, Peter
Bros, Maxime
Machine Learning
Cryptography and Security
68
I.2; I.6; E.3
This work addresses the problem of planting and defending cryptographic-based backdoors in artificial intelligence (AI) models. The motivation comes from our lack of understanding and the implications of using cryptographic techniques for planting undetectable backdoors under theoretical assumptions in the large AI model systems deployed in practice. Our approach is based on designing a web-based simulation playground that enables planting, activating, and defending cryptographic backdoors in neural networks (NN). Simulations of planting and activating backdoors are enabled for two scenarios: in the extension of NN model architecture to support digital signature verification and in the modified architectural block for non-linear operators. Simulations of backdoor defense against backdoors are available based on proximity analysis and provide a playground for a game of planting and defending against backdoors. The simulations are available at https://pages.nist.gov/nn-calculator
title Interactive Simulations of Backdoors in Neural Networks
topic Machine Learning
Cryptography and Security
68
I.2; I.6; E.3
url https://arxiv.org/abs/2405.13217