Please use this identifier to cite or link to this item:
|Title:||A framework for evaluating image obfuscation under deep learning-assisted privacy attacks||Authors:||Tekli, Jimmy
Bouna, Bechara al
Zeinab, al Zein
|Affiliations:||Department of Mechatronics Engineering||Keywords:||Data privacy
|Issue Date:||2019||Part of:||2019 17th International Conference on Privacy, Security and Trust (PST)||Start page:||1||End page:||10||Conference:||International Conference on Privacy, Security and Trust (PST) (17th : 26-28 Aug. 2019 : Fredericton, NB, Canada)||Abstract:||
Computer vision applications such as object detection and recognition, allow machines to visualize and perceive their environments. Nevertheless, these applications are guided by learning-based methods that require capturing, storing and processing large amounts of images thus rendering privacy and anonymity a major concern. In return, image obfuscation techniques (i.e., pixelating, blurring, and masking) have been developed to protect the sensitive information in images. In this paper, we propose a framework to evaluate and recommend the most robust obfuscation techniques in a specific domain of application. The proposed framework reconstructs obfuscated faces via deep learning-assisted attacks and assesses the reconstructions using structural/identity-based metrics. To evaluate and validate our approach, we conduct our experiments on a publicly available celebrity faces dataset. The obfuscation techniques considered are pixelating, blurring and masking. We evaluate the faces reconstructions against five deep learning-assisted privacy attackers. The most resilient obfuscation technique is recommended with regard to structural and identity-based metrics.
|URI:||https://scholarhub.balamand.edu.lb/handle/uob/577||Ezproxy URL:||Link to full text||Type:||Conference Paper|
|Appears in Collections:||Department of Mechatronics Engineering|
Show full item record
checked on Aug 7, 2022
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.