Titre
Towards AI forensics: Did the artificial intelligence system do it?
Type
article
Institution
UNIL/CHUV/Unisanté + institutions partenaires
Auteur(s)
Schneider, Johannes
Auteure/Auteur
Breitinger, Frank
Auteure/Auteur
Liens vers les personnes
Liens vers les unités
ISSN
2214-2126
Statut éditorial
Publié
Date de publication
2023
Volume
76
Première page
103517
Peer-reviewed
Oui
Langue
anglais
Résumé
Artificial intelligence (AI) makes decisions impacting our daily lives in an increasingly autonomous manner. Their actions might cause accidents, harm, or, more generally, violate regulations. Determining whether an AI caused a specific event and, if so, what triggered the AI’s action, are key forensic questions. We provide a conceptualization of the problems and strategies for forensic investigation. We focus on AI that is potentially “malicious by design” and gray box analysis. Our evaluation using convolutional neural networks illustrates challenges and ideas for identifying malicious AI.
Sujets
PID Serval
serval:BIB_4FBA3E9269CA
Open Access
Oui
Date de création
2023-06-07T14:08:13.000Z
Date de création dans IRIS
2025-05-20T18:00:35Z
Fichier(s)![Vignette d'image]()
En cours de chargement...
Nom
1-s2.0-S2214212623001011-main.pdf
Version du manuscrit
published
Licence
https://creativecommons.org/licenses/by/4.0
Taille
2.86 MB
Format
Adobe PDF
PID Serval
serval:BIB_4FBA3E9269CA.P001
URN
urn:nbn:ch:serval-BIB_4FBA3E9269CA7
Somme de contrôle
(MD5):ec4f31d1ac8a6973768a8f2c51a99189