Defeating face de-identification methods based on DCT-block scrambling

Rashwan, Hatem A.; García, Miguel Ángel; Martínez-Ballesté, Antoni; Puig, Domènec

doi:10.1007/s00138-015-0743-5

Cited by 4 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reversible adaptive filters include scrambling [5], [10]- [12], [25]- [27], warping [28] and morphing [29]. While reversible adaptive filters are robust against a parrot attack, their protected faces can be compromised by spatial-domain [30], [31] or frequencydomain attacks [32].…”

Section: Introductionmentioning

confidence: 99%

A Privacy-Preserving Filter for Oblique Face Images Based on Adaptive Hopping Gaussian Mixtures

2019

View full text Add to dashboard Cite

Photographs taken in public places often contain faces of bystanders thus leading to a perceived or actual violation of privacy. To address this issue, we propose to pseudo-randomly modify the appearance of face regions in the images using a privacy filter that prevents a human or a face recogniser from inferring the identity of people. The filter, which is applied only when the resolution is high enough for a face to be recognisable, adaptively distorts the face appearance as a function of its resolution. Moreover, the proposed filter locally changes the values of its parameters to counter attacks that attempt to estimate them. The filter exploits both global adaptiveness to reduce distortion and local parameter hopping to make their estimation difficult for an attacker. In order to evaluate the efficiency of the proposed approach, we consider an important scenario of oblique face images: photographs taken with low altitude Micro Aerial Vehicles (MAVs). We use a state-of-the-art face recognition algorithm and synthetically generated face data with 3D geometric image transformations that mimic faces captured from an MAV at different heights and pitch angles. Experimental results show that the proposed filter protects privacy while reducing distortion, and is also robust against attacks.INDEX TERMS Image privacy protection, hopping Gaussian blur, micro aerial vehicles.

show abstract

Section: Introductionmentioning

confidence: 99%

A Privacy-Preserving Filter for Oblique Face Images Based on Adaptive Hopping Gaussian Mixtures

2019

View full text Add to dashboard Cite

show abstract

“…2008; Ruchaud and Dugelay, 2017;Sohn et al, 2011), warping (Korshunov and Ebrahimi, 2013b) and morphing (Korshunov and Ebrahimi, 2013a). While reversible adaptive filters are robust against a parrot attack, their protected faces can be compromised by spatial-domain (Jiang et al, 2016a,b) or frequency-domain attacks (Rashwan et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

Concealing the identity of faces in oblique images with adaptive hopping Gaussian mixtures

Sarwar¹,

Rinner²,

Cavallaro³

2018

Preprint

View full text Add to dashboard Cite

Cameras mounted on Micro Aerial Vehicles (MAVs) are increasingly used for recreational photography. However, aerial photographs of public places often contain faces of bystanders thus leading to a perceived or actual violation of privacy. To address this issue, we propose to pseudo-randomly modify the appearance of face regions in the images using a privacy filter that prevents a human or a face recogniser from inferring the identities of people. The filter, which is applied only when the resolution is high enough for a face to be recognisable, adaptively distorts the face appearance as a function of its resolution. Moreover, the proposed filter locally changes its parameters to discourage attacks that use parameter estimation. The filter exploits both global adaptiveness to reduce distortion and local hopping of the parameters to make their estimation difficult for an attacker. In order to evaluate the efficiency of the proposed approach, we use a state-of-the-art face recognition algorithm and synthetically generated face data with 3D geometric image transformations that mimic faces captured from an MAV at different heights and pitch angles. Experimental results show that the pro-

show abstract

A Novel Steganography Algorithm Based on Quantization Table Modification and Image Scrambling in DCT Domain

Dai

Cheng

2020

Int. J. Patt. Recogn. Artif. Intell.

View full text Add to dashboard Cite

In this paper, a steganography algorithm has been proposed which is based on quantization table modification and image scrambling in the DCT domain. First, the algorithm homogenizes the energy by scrambling the cover image to improve the number of DCT coefficients suitable for information embedding. Second, the embedding capacity of the DCT block is determined by the value of the quantization table in the algorithm, different quantization tables get different embedding effects. In addition, this paper proposes an optimized modified quantization table. Extensive experiments show that the proposed algorithm achieves a great potential for confidential data and indiscernible image quality.

show abstract

Defeating face de-identification methods based on DCT-block scrambling

Cited by 4 publications

References 23 publications

A Privacy-Preserving Filter for Oblique Face Images Based on Adaptive Hopping Gaussian Mixtures

A Privacy-Preserving Filter for Oblique Face Images Based on Adaptive Hopping Gaussian Mixtures

Concealing the identity of faces in oblique images with adaptive hopping Gaussian mixtures

A Novel Steganography Algorithm Based on Quantization Table Modification and Image Scrambling in DCT Domain

Contact Info

Product

Resources

About