Arc2Morph: Identity-Preserving Facial Morphing with Arc2Face

Nicolò Di Domenico; Annalisa Franco; Matteo Ferrara; Davide Maltoni

cs.CVFeb 18, 2026

Arc2Morph: Identity-Preserving Facial Morphing with Arc2Face

Authors: Nicolò Di Domenico, Annalisa Franco, Matteo Ferrara, Davide Maltoni

Organizations: Department of Computer Science and Engineering, University of Bologna, Italy

Abstract

Face morphing attacks are widely recognized as one of the most challenging threats to face recognition systems used in electronic identity documents. These attacks exploit a critical vulnerability in passport enrollment procedures adopted by many countries, where the facial image is often acquired without a supervised live capture process. In this paper, we propose a novel face morphing technique based on Arc2Face, an identity-conditioned face foundation model capable of synthesizing photorealistic facial images from compact identity representations. We demonstrate the effectiveness of the proposed approach by comparing the morphing attack potential metric on two large-scale sequestered face morphing attack detection datasets against several state-of-the-art morphing methods, as well as on two novel morphed face datasets derived from FEI and ONOT. Experimental results show that the proposed deep learning-based approach achieves a morphing attack potential comparable to that of landmark-based techniques, which have traditionally been regarded as the most challenging. These findings confirm the ability of the proposed method to effectively preserve and manage identity information during the morph generation process.

Figures & tables

Panel of Figure 1 — Fig. 1 : Samples of morphed images (center column) generated with our proposed method. On the first row, Accomplice (left column) and criminal (right column) are sourced from the ONOT [ 10 ] dataset; on the second row, accomplice and criminal are sourced from the FEI [ 46 ] dataset.

Fig. 2 : Overview of the proposed method. The input images $I_{A}$ and $I_{B}$ are first encoded using the identity encoder $E_{i}d(\cdot)$ , producing the identity embeddings $e_{A}$ and $e_{B}$ . In parallel, we extract the pose conditioning image for Arc2Face with EMOCAv2 [ 6 , 19 ] , obtaining $I_{P}$ . Then, the two compact identity representations $e_{A}$ and $e_{B}$ are mapped into the CLIP latent space and interpolated to obtain the latent representation $p_{M}$ , which is then decoded alongside with the conditioning image $I_{P}$ to generate the morphed image $I_{M}^{\prime}$ . Finally, the resulting image is post-processed using BEN2 to remove the background, yielding the final morphed image $I_{M}$ .

Algorithm	Type	FEI Morph v2	MONOT	EINMorph-HQ v2	EINMorph-MQ v2
C01 [ 41 ]	L	$\times$	$\times$
C02 [ 13 ]	L	$\times$	$\times$
C03 [ 43 ]	L	$\times$	$\times$
C05 [ 16 ]	L	$\times$	$\times$
C05-PA97 [ 16 ] [ 50 ] 1 1 1 Morphed images generated using the C05 approach [ 16 ] were subsequently retouched to remove morphing artifacts by applying a face restoration technique.	L			$\times$	$\times$
C05-PA98 [ 16 ] [ 49 ] 1	L			$\times$	$\times$

TABLE I: List of the morphing algorithms used to generate the morphed images for the datasets considered in this work. The column Type indicates whether the corresponding method is based on facial landmarks (L) or on deep learning techniques (D).

	1	2	3
C01	97.9%	91.7%	74.0%
C02	99.7%	98.9%	95.9%
C03	97.3%	89.9%	70.2%
C05	98.4%	93.5%	78.0%
C08	98.6%	94.4%	82.5%
C15	97.7%	91.5%	70.9%

TABLE II : MAP computed on the FEI Morph v2 dataset for the proposed approach and seven competitors. Best results for each column are highlighted in bold. In this case, a single probe image is available, so the MAP of each algorithm is represented by a single row.

	1	2	3
C01	94.2%	86.7%	73.5%
C02	94.1%	86.7%	74.0%
C03	90.9%	80.8%	63.4%
C05	91.8%	83.0%	67.4%
C15	89.3%	78.3%	55.8%
C16	91.8%	82.3%	61.6%

TABLE III : MAP computed on the MONOT dataset for the proposed approach and the six competitors reported in [ 3 ] , considering a single ONOT image for each subject as probe(the MAP of each algorithm is represented by a single row). Best results for each column are highlighted in bold.

	1	2	3
1	100.0%	100.0%	99.9%
2	100.0%	100.0%	99.8%
3	100.0%	100.0%	99.8%
4	100.0%	100.0%	99.6%
5	100.0%	100.0%	99.6%
6	100.0%	99.9%	99.1%

TABLE IV : MAP computed on the MONOT dataset for the proposed approach, considering ten ”in the wild” images for each subject as probe.

Panel of Figure 7 — Fig. 3 : Visualization of the MAPs computed on the MONOT dataset for the proposed approach and the competitors, considering ten ”in the wild” images as probe.

Panel of Figure 8 — Fig. 4 : Visualization of the MAPs computed on the EINMorph-HQ v2 dataset for the proposed approach and the competitors.

Panel of Figure 9 — Fig. 5 : Visualization of the MAPs computed on the EINMorph-MQ v2 dataset for the proposed approach and the competitors.

Panel of Figure 10 — Fig. 6 : A visual example of the morphed images obtained using the different interpolation approaches, given the same image pair as input.

Dataset	Interp. location	$f_{interp}$	$MAP_{Avg}$
FEI	Identity	lerp	0.9778
	Identity	slerp	0.9679
	CLIP	lerp	0.9747
	CLIP	slerp	0.9835
MONOT	Identity	lerp	0.8539
	Identity	slerp	0.8486

TABLE V :

MAP_{Avg}

reported on FEI and MONOT datasets for each choice of interpolation location ( i.e. , identity-level or CLIP latent-level) and interpolation function

f_{interp}

( i.e. , linear interpolation or spherical linear interpolation).

Identity-Preserving Image Generation

Identity-preserving image generation creates or edits images while retaining a person's recognizable features across changes in pose, style, or scene.

See all 48 papers

DCMorph: Face Morphing via Dual-Stream Cross-Attention Diffusion
Apr 23, 2026Tahar Chettaoui, Eduarda Caldeira, Guray Ozgur +3Identity-Preserving Image Generation Conditional Diffusion Models
Fraunhofer Institute for Computer Graphics Research IGD, Germany · TU Darmstadt, Germany · Norwegian University of Science and Technology (NTNU), Norway
R-FLoRA: Residual-Statistic-Gated Low-Rank Adaptation for Single-Image Face Morphing Attack Detection
Apr 19, 2026Raghavendra RamachandraImage Forgery Detection Vision Foundation Model Adaptation
SAFE Center, Department of Information Security and Communication Technology, Norwegian University of Science and Technology (NTNU), Norway
SFDemorpher: Generalizable Face Demorphing for Operational Morphing Attack Detection
Mar 30, 2026Raul Ismayilov, Luuk SpreeuwersImage Forgery Detection Representation Disentanglement
Data Management & Biometrics, University of Twente, Drienerlolaan 5, Enschede, 7512AD, Netherlands.

Apr 23, 2026J/K move · Enter open · S save

DCMorph: Face Morphing via Dual-Stream Cross-Attention Diffusion

Tahar Chettaoui, Eduarda Caldeira, Guray Ozgur, Raghavendra Ramachandra+2

Fraunhofer Institute for Computer Graphics Research IGD, Germany · TU Darmstadt, Germany · Norwegian University of Science and Technology (NTNU), Norway

Identity-Preserving Image Generation Conditional Diffusion Models

Open paper AskPDF arXiv

Advancing face morphing attack techniques is crucial to anticipate evolving threats and develop robust defensive mechanisms for identity verification systems. This work introduces DCMorph, a dual-stream diffusion-based morphing framework that simultaneously operates at both identity conditioning and latent space levels. Unlike image-level methods suffering from blending artifacts or GAN-based approaches with limited reconstruction fidelity, DCMorph leverages identity-conditioned latent diffusion models through two mechanisms: (1) decoupled cross-attention interpolation that injects identity-specific features from both source faces into the denoising process, enabling explicit dual-identity conditioning absent in existing diffusion-based methods, and (2) DDIM inversion with spherical interpolation between inverted latent representations from both source faces, providing geometrically consistent initial latent representation that preserves structural attributes. Vulnerability analyses across four state-of-the-art face recognition systems demonstrate that DCMorph achieves the highest attack success rates compared to existing methods at both operational thresholds, while remaining challenging to detect by current morphing attack detection solutions.

Abstract

Identity-Preserving Image Generation

Explore similar work

DCMorph: Face Morphing via Dual-Stream Cross-Attention Diffusion

R-FLoRA: Residual-Statistic-Gated Low-Rank Adaptation for Single-Image Face Morphing Attack Detection

SFDemorpher: Generalizable Face Demorphing for Operational Morphing Attack Detection