Detecting Insecure Authentication Flows at Design Time with Graph Machine Learning

Research unit

INNOSUISSE

Project number

136.969 INNO-ICT

Project title

Detecting Insecure Authentication Flows at Design Time with Graph Machine Learning

Texts for this project

	German	French	Italian	English
Key words	-	-	-
Abstract	-	-	-

Category	Text
Key words (English)	ICT, IT security and cryptography
Abstract (English)	Modern IAM systems let non-experts design login flows visually, but small mistakes can open serious security gaps. This feasibility study explores using graph machine learning to analyse these flows as they are built and to highlight insecure configurations before they ever reach production.