Detection of Face Morphing Attacks by Deep Learning

Seibold, Clemens; Samek, Wojciech; Hilsmann, Anna; Eisert, Peter

doi:10.1007/978-3-319-64185-0_9

Cited by 90 publications

(73 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image morphing is a longstanding research topic in computer graphics and computer vision, e.g. [36,29,30,32,38,17]). Given two embedded images with their respective latent vectors w 1 and w 2 , morphing is computed by a linear interpolation, w = λw 1 + (1 − λ)w 2 , λ ∈ (0, 1), and subsequent image generation using the new code w. As Figure 4 shows, our method generates high-quality morphing between face images (row 1,2,3) but fails on non-face images in both in-class (row 4) and inter-class (row 5) morphing.…”

Section: Morphingmentioning

confidence: 99%

Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?

Abdal

Qin

Wonka

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

915

781

View full text Add to dashboard Cite

We propose an efficient algorithm to embed a given image into the latent space of StyleGAN. This embedding enables semantic image editing operations that can be applied to existing photographs. Taking the StyleGAN trained on the FFHQ dataset as an example, we show results for image morphing, style transfer, and expression transfer. Studying the results of the embedding algorithm provides valuable insights into the structure of the StyleGAN latent space. We propose a set of experiments to test what class of images can be embedded, how they are embedded, what latent space is suitable for embedding, and if the embedding is semantically meaningful.

show abstract

Section: Morphingmentioning

confidence: 99%

Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?

Abdal

Qin

Wonka

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

915

781

View full text Add to dashboard Cite

show abstract

“…In case of the deep learning techniques, we have used the pre-trained network and computed the corresponding features that are further classified using a linear Support Vector Machines (SVM). To this extent, we have considered pre-trained CNN such as AlexNet [11,33,34], GoogleNet [33], Inception V3 [33], ResNet101 [11,33,34], VGG16 [11,33,9] and VGG19 [11,33,9]. The deep-learning techniques are used only as the feature extraction techniques owing to the availability of the small datasets.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…Following this work, several other works are reported [21,7] using the capability of micro-texture extraction techniques that can effectively capture the variations to reflect the process of morphing, which aids the morph detection task. Lately, the use of pre-trained deep CNNs with different architectures are widely studied in [5,9,11]. Further, the combination of deep features with handcrafted features is proposed in [10].…”

Section: Related Workmentioning

confidence: 99%

Detecting Morphed Face Attacks Using Residual Noise from Deep Multi-scale Context Aggregation Network

Venkatesh¹,

Ramachandra²,

Raja³

et al. 2020

Preprint

View full text Add to dashboard Cite

Along with the deployment of the Face Recognition Systems (FRS), concerns were raised related to the vulnerability of those systems towards various attacks including morphed attacks. The morphed face attack involves two different face images in order to obtain via a morphing process a resulting attack image, which is sufficiently similar to both contributing data subjects. The obtained morphed image can successfully be verified against both subjects visually (by a human expert) and by a commercial FRS. The face morphing attack poses a severe security risk to the e-passport issuance process and to applications like border control, unless such attacks are detected and mitigated. In this work, we propose a new method to reliably detect a morphed face attack using a newly designed denoising framework. To this end, we design and introduce a new deep Multi-scale Context Aggregation Network (MS-CAN) to obtain denoised images, which is subsequently used to determine if an image is morphed or not. Extensive experiments are carried out on three different morphed face image datasets. The Morphing Attack Detection (MAD) performance of the proposed method is also benchmarked against 14 different state-of-the-art techniques using the ISO-IEC 30107-3 evaluation metrics. Based on the obtained quantitative results, the proposed method has indicated the best performance on all three datasets and also on cross-dataset experiments.

show abstract

“…Several researchers become aware of the danger of morphing attacks and developed different forensic methods to detect this kind of fraud. In contrast to the already proposed methods, which are based on image degeneration [4], Binarized Statistical Image Features (BSIF) [5], neural networks [6], [7] or JPEG compression artifacts [8], we propose a method that is based on a physical illumination model. Illumination estimation to detect frauds was already studied in detail by [9], [10] to detect compositions of multiple photographs.…”

Section: Introductionmentioning

confidence: 99%

Reflection Analysis for Face Morphing Attack Detection

Seibold

Hilsmann

Eisert

2018

2018 26th European Signal Processing Conference (EUSIPCO)

Self Cite

View full text Add to dashboard Cite

A facial morph is a synthetically created image of a face that looks similar to two different individuals and can even trick biometric facial recognition systems into recognizing both individuals. This attack is known as face morphing attack. The process of creating such a facial morph is well documented and a lot of tutorials and software to create them are freely available. Therefore, it is mandatory to be able to detect this kind of fraud to ensure the integrity of the face as reliable biometric feature. In this work, we study the effects of face morphing on the physically correctness of the illumination. We estimate the direction to the light sources based on specular highlights in the eyes and use them to generate a synthetic map for highlights on the skin. This map is compared with the highlights in the image that is suspected to be a fraud. Morphing faces with different geometries, a bad alignment of the source images or using images with different illuminations, can lead to inconsistencies in reflections that indicate the existence of a morphing attack.

show abstract

Detection of Face Morphing Attacks by Deep Learning

Cited by 90 publications

References 20 publications

Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?

Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?

Detecting Morphed Face Attacks Using Residual Noise from Deep Multi-scale Context Aggregation Network

Reflection Analysis for Face Morphing Attack Detection

Contact Info

Product

Resources

About