Find the Differences: Differential Morphing Attack Detection vs Face Recognition

arXiv cs.CV / 4/17/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper argues that face recognition (FR) and differential morphing attack detection (D-MAD) solve essentially similar problems, supported by side-by-side comparisons with two existing D-MAD methods.
It shows that common decision thresholds used in FR systems make them intrinsically vulnerable to morphing attacks, linking this vulnerability to the normal-vs-morphing performance tradeoff.
The authors propose leveraging already-deployed FR systems for morphing detection rather than building entirely separate pipelines.
They introduce a new evaluation threshold intended to cap the maximum vulnerability to morphing attacks, including previously unknown morphing types.

Abstract

Morphing is a challenge to face recognition (FR) for which several morphing attack detection solutions have been proposed. We argue that face recognition and differential morphing attack detection (D-MAD) in principle perform very similar tasks, which we support by comparing an FR system with two existing D-MAD approaches. We also show that currently used decision thresholds inherently lead to FR systems being vulnerable to morphing attacks and that this explains the tradeoff between performance on normal images and vulnerability to morphing attacks. We propose using FR systems that are already in place for morphing detection and introduce a new evaluation threshold that guarantees an upper limit to the vulnerability to morphing attacks - even of unknown types.