Combining Forensics and Privacy Requirements for Digital Images - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Combining Forensics and Privacy Requirements for Digital Images


This paper proposes to study the impact of image selective encryption on both forensics and privacy preserving mechanisms. The proposed selective encryption scheme works independently on each bitplane by encrypting the s most significant bits of each pixel. We show that this mechanism can be used to increase privacy by mitigating image recognition tasks. In order to guarantee a trade-off between forensics analysis and privacy, the signal of interest used for forensics purposes is extracted from the 8−s least significant bits of the protected image. We show on the CASIA2 database that good tampering detection capabilities can be achieved for s ∈ {3,. .. , 5} with an accuracy above 80% using SRMQ1 features, while preventing class recognition tasks using CNN with an accuracy smaller than 50%.
Fichier principal
Vignette du fichier
EUSIPCO2021.pdf (3.4 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03160123 , version 1 (04-03-2021)
hal-03160123 , version 2 (16-06-2021)



Pauline Puteaux, Vincent Itier, Patrick Bas. Combining Forensics and Privacy Requirements for Digital Images. EUSIPCO 2021 - 29th European Signal Processing Conference, Aug 2021, Dublin (virtual), Ireland. pp.806-810, ⟨10.23919/EUSIPCO54536.2021.9616041⟩. ⟨hal-03160123v2⟩
130 View
87 Download



Gmail Facebook Twitter LinkedIn More