Face Morphing, a Modern Threat to Border Security: Recent Advances and Open Challenges

Abstract

Face morphing poses a serious threat to Automatic Border Control (ABC) and Face Recognition Systems (FRS) in general. The aim of this paper is to present a qualitative assessment of the morphing attack issue, and the challenges it entails, highlighting both the technological and human aspects of the problem. Here, after the face morphing attack scenario is presented, the paper provides an overview of the relevant bibliography and recent advances towards two central directions. First, the morphing of face images is outlined with a particular focus on the three main steps that are involved in the process, namely, landmark detection, face alignment and blending. Second, the detection of morphing attacks is presented under the prism of the so-called on-line and off-line detection scenarios and whether the proposed techniques employ handcrafted features, using classical methods, or automatically generated features, using deep-learning-based methods. The paper, then, presents the evaluation metrics that are employed in the corresponding bibliography and concludes with a discussion on open challenges that need to be address for further advancing automatic detection of morphing attacks. Despite the progress being made, the general consensus of the research community is that significant effort and resources are needed in the near future for the mitigation of the issue, especially, towards the creation of datasets capturing the full extent of the problem at hand and the availability of reference evaluation procedures for comparing novel automatic attack detection algorithms.

Techniques and Challenges for Generation and Detection Face Morphing Attacks: A Survey

“…A. The process of creating a morphing image faces many challenges, including [13,19]: 1. Using more than one image for several people and producing face morphing is difficult because the differences in the image textures and features will increase.…”

“…The reason for this is that the stored image eMRTD contains modifications, which means when creating a passport, two photos of the traveler and another person are combined, resulting in an image that contains part of the first person and part of the other person. This condition is called a morphing face [13,14]. Figure 1 represent morph image.…”

Psychophysical Evaluation of Human Performance in Detecting Digital Face Image Manipulations

“…With more and more extensive deployment of face recognition technology in security-critical areas, specifically for applications in law enforcement and border control [37]- [39], face image manipulations present a serious threat in these operational contexts and to face recognition processes in general. This in turn has prompted sustained interest and work relating to detection methods for certain face image manipulations [40], in addition to aforementioned regulatory measures [21].…”

Identifying and minimising the impact of fake visual media: Current and future directions

“…Face morphs are created by digitally combining images of two or more individuals to create a new image that resembles each of the original identities. The wide availability of face morphing software means that this type of fake image now poses a serious threat to border controls and other face recognition systems used in security settings (see Pikoulis et al 2021), and worryingly, several studies show that people cannot reliably detect face morphs (Kramer et al 2019;Nightingale et al 2021;Robertson et al 2017Robertson et al , 2018. In one recent study, participants attempted to determine whether two face images depicted the same person or not (Robertson et al 2017).…”