MorphUNet: Alpha-Controlled Biometric Transport for Diffusion-Based Face Morphing Attacks

MorphUNet, a diffusion-based face morphing framework introduced in a new arXiv preprint (2607.25092v1), achieves the best Morphing Attack Potential (MAP) of 0.919 on FEI and 0.886 on FRLL when at least three of six recognition systems are fooled by a single morph, outperforming StableMorph, MIPGAN-II, and MorDIFF. The framework uses alpha-controlled biometric transport with parent-separated dual cross-attention and achieves the best FID scores of 35.19 on FEI and 44.86 on FRLL, while remaining highly difficult to detect under cross-dataset transfer with APCER values of 0.996 and 0.946 respectively.

arXiv:2607.25092v1 Announce Type: new Abstract: Face morphing attacks create synthetic images verifiable against multiple identities, threatening border control and identity verification systems. We introduce MorphUNet, a diffusion morphing framework formulating two-parent generation as alpha-controlled biometric transport: each parent is decomposed into CLIP appearance and ArcFace identity evidence, aligned into a CLIP-compatible token space, with the two contributors preserved as separate identity-aware token banks. To our knowledge, MorphUNet is the first diffusion-based morphing framework using trainable parent-separated dual cross-attention inside the denoising U-Net: a Biometric Transport Layer carrying parent-specific identity evidence through denoising, attending to each parent separately before combining residuals via the morphing parameter alpha. DDIM-inverted latent interpolation gives a coherent denoising start, while weaker-parent-guided selection favours morphs maximising the lower parent-similarity score, reducing collapse toward one contributor. We evaluate MorphUNet against three state-of-the-art baselines StableMorph, MIPGAN-II, and MorDIFF on FEI and FRLL using six recognition systems, and propose CFD-based unseen-identity stress testing across gender and ethnicity pairing, demographic shifts, and parent-similarity extremes. MorphUNet achieves the best Morphing Attack Potential MAP when at least three of six systems are fooled by one morph, reaching 0.919 on FEI and 0.886 on FRLL, and obtains the best FID on both datasets 35.19 FEI, 44.86 FRLL . It also gives the highest APCER at 5% BPCER in the same-dataset setting, and remains highly difficult to detect under cross-dataset transfer, with APCER 0.996 on FEI and 0.946 on FRLL. The full evaluation analyses MAP, MAD, per-system vulnerability, identity balance, image quality, top/bottom-similarity stress tests, and CFD unseen-identity robustness.