SYN-MAD 2022: Competition on Face Morphing Attack Detection Based on Privacy-aware Synthetic Training Data

Huber, Marco F.; Thi, Luu, Anh; Raja, Kiran B.; Ramachandra, Raghavendra; Damer, Naser; Neto, Pedro C.; Gonçalves, Tiago; Sequeira, Ana F.; Cardoso, Jaime S.; Tremoço, João; Lourenço, Miguel Rodrigues; Serra, Sergio; Cermeño, Eduardo; Ivanovska, Marija; Batagelj, Borut; Kronovsek, Andrej; Peer, Peter

doi:10.1109/ijcb54206.2022.10007950

Cited by 17 publications

(5 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data that support the findings of this study are openly available in “SYN‐MAD‐2022″” at https://doi.org/10.1109/IJCB54206.2022.10007950, reference number [38]. The data that support the findings of this study are openly available in “HNU‐FM” at https://doi.org/10.1109/10.1109/ICEITSA54226.2021.00082, reference number [37].…”

Section: Data Availability Statementmentioning

confidence: 57%

See 1 more Smart Citation

ADFF: Adaptive de‐morphing factor framework for restoring accomplice's facial image

Long,

Zhou,

Zhang

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Morphing attacks (MAs) pose a substantial security threat to the Automatic Border Control (ABC) system. While a few morphing attack detection (MAD) methods have been proposed, the face morphing accomplice's facial restoration has not received sufficient attention. Due to the inability to foresee the morphing factor used for a particular morphed image, selecting the appropriate de‐morphing factor becomes a challenging problem in the restoration of the accomplice's facial image. If the morphing factor cannot be chosen reasonably, achieving the desired restoration effect is difficult. Therefore, this paper presents an adaptive de‐morphing factor framework (ADFF) architecture for restoring the accomplice's facial image. By exploiting the morphed images stored in the electronic passport system and the real‐time captured criminal's images, ADFF can effectively restore the accomplice's facial image. Experimental results and analysis show that ADFF can significantly reduce the security threats of MAs on ABC.

show abstract

Section: Data Availability Statementmentioning

confidence: 57%

“…HNU‐FM [37] and SYN‐FACE [38] were chosen to evaluate the proposed ADFF. The HNU‐FM dataset is created based on facial landmarks, while the SYN‐FACE dataset is created based on GAN.…”

Section: Experiments and Analysismentioning

confidence: 99%

ADFF: Adaptive de‐morphing factor framework for restoring accomplice's facial image

Long,

Zhou,

Zhang

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Thus they can be considered to be challenging, similarly to other attack types, to be detected by the MADs. In general, the MixFaceNet-MAD performed slightly better than the Inception-MAD in most cases, whether to detect MorDIFF or other attacks, keeping in mind that this MAD (trained on SMDD) was the baseline for the recent SYN-MAD 2022 competition [22]. MoreDiff attacks seem to be also detected relatively better when the MADs are trained on the SMDD dataset.…”

Section: Fr Modelmentioning

confidence: 87%

“…IV. THE MORDIFF DATASET The MorDIFF dataset extends over the SYN-MAD 2022 competition dataset [22] and uses the same morphing pairs to enable a comparable dataset set. The MorDIFF and the SYN-MAD 2022 datasets are both based on the Face Research Lab London (FRLL) dataset [14].…”

Section: Diffusion-based Face Morphingmentioning

confidence: 99%

MorDIFF: Recognition Vulnerability and Attack Detectability of Face Morphing Attacks Created by Diffusion Autoencoders

Damer¹,

Fang²,

Siebke³

et al. 2023

Preprint

View full text Add to dashboard Cite

Investigating new methods of creating face morphing attacks is essential to foresee novel attacks and help mitigate them. Creating morphing attacks is commonly either performed on the image-level or on the representation-level. The representation-level morphing has been performed so far based on generative adversarial networks (GAN) where the encoded images are interpolated in the latent space to produce a morphed image based on the interpolated vector. Such a process was constrained by the limited reconstruction fidelity of GAN architectures. Recent advances in the diffusion autoencoder models have overcome the GAN limitations, leading to high reconstruction fidelity. This theoretically makes them a perfect candidate to perform representation-level face morphing. This work investigates using diffusion autoencoders to create face morphing attacks by comparing them to a wide range of imagelevel and representation-level morphs. Our vulnerability analyses on four state-of-the-art face recognition models have shown that such models are highly vulnerable to the created attacks, the MorDIFF, especially when compared to existing representationlevel morphs. Detailed detectability analyses are also performed on the MorDIFF, showing that they are as challenging to detect as other morphing attacks created on the image-or representationlevel. Data and morphing script is made public 1 .

show abstract

“…One of the main candidate solutions for this issue is the use of synthetic data [8]. This has been very recently and successfully proposed for the training of face recognition [4,5,30] and morphing attack detection [9,11,21], among other processes such as model quantization [2]. Synthetic data for PAD development has, besides the privacy and legal motivations, a major advantage when it comes to scale and diversity.…”

Section: Introductionmentioning

confidence: 99%

SynthASpoof: Developing Face Presentation Attack Detection Based on Privacy-friendly Synthetic Data

Fang¹,

Huber²,

Damer³

2023

Preprint

View full text Add to dashboard Cite

Recently, significant progress has been made in face presentation attack detection (PAD), which aims to secure face recognition systems against presentation attacks, owing to the availability of several face PAD datasets. However, all available datasets are based on privacy and legallysensitive authentic biometric data with a limited number of subjects. To target these legal and technical challenges, this work presents the first synthetic-based face PAD dataset, named SynthASpoof, as a large-scale PAD development dataset. The bona fide samples in SynthASpoof are synthetically generated and the attack samples are collected by presenting such synthetic data to capture systems in a real attack scenario. The experimental results demonstrate the feasibility of using SynthASpoof for the development of face PAD. Moreover, we boost the performance of such a solution by incorporating the domain generalization tool MixStyle into the PAD solutions. Additionally, we showed the viability of using synthetic data as a supplement to enrich the diversity of limited authentic training data and consistently enhance PAD performances. The SynthASpoof dataset, containing 25,000 bona fide and 78,800 attack samples, the implementation, and the pre-trained weights are made publicly available 1 .

show abstract

SYN-MAD 2022: Competition on Face Morphing Attack Detection Based on Privacy-aware Synthetic Training Data

Cited by 17 publications

References 38 publications

ADFF: Adaptive de‐morphing factor framework for restoring accomplice's facial image

ADFF: Adaptive de‐morphing factor framework for restoring accomplice's facial image

MorDIFF: Recognition Vulnerability and Attack Detectability of Face Morphing Attacks Created by Diffusion Autoencoders

SynthASpoof: Developing Face Presentation Attack Detection Based on Privacy-friendly Synthetic Data

Contact Info

Product

Resources

About