ADMIn: Attacks on Dataset, Model and Input: A Threat Model for AI Based Software

Vimal Kumar, Juliette Mayo, Khadija Bahiss

2024

Abstract

Machine learning (ML) and artificial intelligence (AI) techniques have now become commonplace in software products and services. When threat modelling a system, it is therefore important that we consider threats unique to ML and AI techniques, in addition to threats to our software. In this paper, we present a threat model that can be used to systematically uncover threats to AI based software. The threat model consists of two main parts, a model of the software development process for AI based software and an attack taxonomy that has been developed using attacks found in adversarial AI research. We apply the threat model to two real life AI based software and discuss the process and the threats found.

Paper Citation

in Harvard Style

Kumar V., Mayo J. and Bahiss K. (2024). ADMIn: Attacks on Dataset, Model and Input: A Threat Model for AI Based Software. In Proceedings of the 10th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP; ISBN 978-989-758-683-5, SciTePress, pages 170-178. DOI: 10.5220/0012394100003648

in Bibtex Style

@conference{icissp24,
author={Vimal Kumar and Juliette Mayo and Khadija Bahiss},
title={ADMIn: Attacks on Dataset, Model and Input: A Threat Model for AI Based Software},
booktitle={Proceedings of the 10th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP},
year={2024},
pages={170-178},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012394100003648},
isbn={978-989-758-683-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 10th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP
TI - ADMIn: Attacks on Dataset, Model and Input: A Threat Model for AI Based Software
SN - 978-989-758-683-5
AU - Kumar V.
AU - Mayo J.
AU - Bahiss K.
PY - 2024
SP - 170
EP - 178
DO - 10.5220/0012394100003648
PB - SciTePress