Accurate and robust neural networks for face morphing attack detection

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

doi:10.1016/j.jisa.2020.102526

Cited by 34 publications

(45 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Here, we explored a basic “proof of concept” model with our images, while more advanced computational techniques are beginning to demonstrate impressively high levels of detection using a variety of approaches (e.g. Seibold, Samek, et al, 2018).…”

Section: Discussionmentioning

confidence: 99%

“…One approach is to develop increasingly sophisticated computer methods for morph detection (e.g. Makrushin, Neubert, & Dittmann, 2017; Neubert, 2017; Raghavendra, Raja, Venkatesh, & Busch, 2017a, 2017b; Scherhag, Nautsch, et al, 2017; Scherhag, Raghavendra, et al, 2017; Seibold, Samek, Hilsmann, & Eisert, 2017, 2018). For example, inconsistencies between the reflections visible in the eyes and skin could signal a morphed image (Seibold, Hilsmann, & Eisert, 2018).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Face morphing attacks: Investigating detection with humans and computers

et al. 2019

View full text Add to dashboard Cite

Background In recent years, fraudsters have begun to use readily accessible digital manipulation techniques in order to carry out face morphing attacks. By submitting a morph image (a 50/50 average of two people’s faces) for inclusion in an official document such as a passport, it might be possible that both people sufficiently resemble the morph that they are each able to use the resulting genuine ID document. Limited research with low-quality morphs has shown that human detection rates were poor but that training methods can improve performance. Here, we investigate human and computer performance with high-quality morphs, comparable with those expected to be used by criminals. Results Over four experiments, we found that people were highly error-prone when detecting morphs and that training did not produce improvements. In a live matching task, morphs were accepted at levels suggesting they represent a significant concern for security agencies and detection was again error-prone. Finally, we found that a simple computer model outperformed our human participants. Conclusions Taken together, these results reinforce the idea that advanced computational techniques could prove more reliable than training people when fighting these types of morphing attacks. Our findings have important implications for security authorities worldwide. Electronic supplementary material The online version of this article (10.1186/s41235-019-0181-4) contains supplementary material, which is available to authorized users.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Face morphing attacks: Investigating detection with humans and computers

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Our method, FLRP, is inspired by the results shown in [25]. The authors used LRP to analyze on which coarse region a DNN for face morphing attack detection focuses for its decision-making.…”

Section: Focused Lrpmentioning

confidence: 99%

“…They also showed that LRP often assigns large relevance scores to artifact-free regions in morphed face images, marking them as relevant for the decision of labeling the images as a morph. In contrast to the studies in [25], which focused on average relevance distributions for a set of images, our study focuses on the independent processing of single images and is intended to provide more transparency for individual decisions of DNNs.…”

Section: Focused Lrpmentioning

confidence: 99%

“…Even though interpretability of DNNs is a prominent research topic, the studies about its applicability to DNN-based face morphing attack detectors are scarce. A recent research regarding this topic has been done by Seibold et al [25]. They use Layer-wise Relevance Propagation (LRP) [1] to analyze on which coarse regions their DNN-based detectors focus and propose a training method that forces their DNNs to include information from all of these regions in the decision-making process.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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