Facing image source attribution on iPhone X

A comparison between the base portrait image, the bokeh portrait image, and the depth map.


Most image forensics techniques rely on the analysis of traces left into the signal during the image acquisition process, which is supposed to be common among most devices. However, recent advances in visual technologies led several manufacturers to customize the acquisition pipeline in order to improve the image quality, by designing alternative coding schemes and in-camera processing. This fact threatens the effectiveness of available forensic techniques. It is thus required to study modern acquisition devices to both assess the effectiveness of available techniques and to develop new effective approaches. In this paper we focus on the source identification of images coming from one of the most spread moderm smartphones, i.e. the iPhone X. This model is significant since it comprises two main new features: the new HEIF compression standard, set as the default image format, and a brand new shooting mode, called Portrait Mode. We show that existing source identification methods are ineffective when images are acquired in Portrait Mode. We also show when and how it is possible to address this limitation by removing non unique artefacts introduced by the camera software.


  title={Facing image source attribution on iPhone X},
  author={Baracchi, Daniele and Iuliani, Massimo and Nencini, Andrea G and Piva, Alessandro},
  booktitle={Digital Forensics and Watermarking: 19th International Workshop, IWDW 2020, Melbourne, VIC, Australia, November 25--27, 2020, Revised Selected Papers 19},


This work was supported in part by the Italian Ministry of Education, Universities and Research (MIUR) under Grant 2017Z595XS.