Vulnerabilities of Connectionist AI Applications: Evaluation and Defense

Vulnerabilities of Connectionist AI Applications: Evaluation and Defense

This article deals with the IT security of connectionist artificial intelligence (AI) applications, focusing on threats to integrity, one of the three IT security goals. Such threats are for instance most relevant in prominent AI computer vision applications. In order to present a holistic view on t...

Full description

Bibliographic Details
Main Authors: Christian Berghoff, Matthias Neu, Arndt von Twickel
Format: Article
Language:English
Published: Frontiers Media S.A. 2020-07-01
Series:Frontiers in Big Data
Subjects:
artificial intelligence
neural network
IT security
interpretability
certification
adversarial attack
Online Access:https://www.frontiersin.org/article/10.3389/fdata.2020.00023/full

Similar Items

Similar Items