Worst-Case Morphs: a Theoretical and a Practical Approach

TL;DR

This paper investigates the worst-case scenarios of face morphing attacks on face recognition systems by constructing theoretical upper bounds and generating images that can fool multiple systems, revealing system vulnerabilities.

Contribution

It introduces a worst-case construction in embedding space and a method to generate morphs that approximate this bound, enhancing understanding of FR system weaknesses.

Findings

Generated morphs can fool unseen FR systems

Theoretical upper bounds are approximated in practice

Method reveals vulnerabilities of face recognition systems

Abstract

Face Recognition (FR) systems have been shown to be vulnerable to morphing attacks. We examine exactly how challenging morphs can become. By showing a worst-case construction in the embedding space of an FR system and using a mapping from embedding space back to image space we generate images that show that this theoretical upper bound can be approximated if the FR system is known. The resulting morphs can also succesfully fool unseen FR systems and are useful for exploring and understanding the weaknesses of FR systems. Our method contributes to gaining more insight into the vulnerability of FR systems.