On the Formal Robustness Evaluation for AI-based Industrial Systems

Mohamed Khedher, Afef Awadid, Augustin Lemesle, Zakaria Chihani

2024

Abstract

The paper introduces a three-stage evaluation pipeline for ensuring the robustness of AI models, particularly neural networks, against adversarial attacks. The first stage involves formal evaluation, which may not always be feasible. For such cases, the second stage focuses on evaluating the model’s robustness against intelligent adversarial attacks. If the model proves vulnerable, the third stage proposes techniques to improve its robustness. The paper outlines the details of each stage and the proposed solutions. Moreover, the proposal aims to help developers build reliable and trustworthy AI systems that can operate effectively in critical domains, where the use of AI models can pose significant risks to human safety.

Paper Citation

in Harvard Style

Khedher M., Awadid A., Lemesle A. and Chihani Z. (2024). On the Formal Robustness Evaluation for AI-based Industrial Systems. In Proceedings of the 12th International Conference on Model-Based Software and Systems Engineering - Volume 1: MBSE-AI Integration; ISBN 978-989-758-682-8, SciTePress, pages 311-321. DOI: 10.5220/0012618100003645

in Bibtex Style

@conference{mbse-ai integration24,
author={Mohamed Khedher and Afef Awadid and Augustin Lemesle and Zakaria Chihani},
title={On the Formal Robustness Evaluation for AI-based Industrial Systems},
booktitle={Proceedings of the 12th International Conference on Model-Based Software and Systems Engineering - Volume 1: MBSE-AI Integration},
year={2024},
pages={311-321},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012618100003645},
isbn={978-989-758-682-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Model-Based Software and Systems Engineering - Volume 1: MBSE-AI Integration
TI - On the Formal Robustness Evaluation for AI-based Industrial Systems
SN - 978-989-758-682-8
AU - Khedher M.
AU - Awadid A.
AU - Lemesle A.
AU - Chihani Z.
PY - 2024
SP - 311
EP - 321
DO - 10.5220/0012618100003645
PB - SciTePress