Provenance analysis for Instagram photos

Yijun Quan; Xufeng Lin; Chang Tsun Li

doi:10.1007/978-981-13-6661-1_29

Provenance analysis for Instagram photos

Yijun Quan, Xufeng Lin, Chang Tsun Li

University of Warwick

Research output: Book chapter/Published conference paper › Conference paper › peer-review

5 Citations (Scopus)

Abstract

As a feasible device fingerprint, sensor pattern noise (SPN) has been proven to be effective in the provenance analysis of digital images. However, with the rise of social media, millions of images are being uploaded to and shared through social media sites every day. An image downloaded from social networks may have gone through a series of unknown image manipulations. Consequently, the trustworthiness of SPN has been challenged in the provenance analysis of the images downloaded from social media platforms. In this paper, we intend to investigate the effects of the pre-defined Instagram images filters on the SPN-based image provenance analysis. We identify two groups of filters that affect the SPN in quite different ways, with Group I consisting of the filters that severely attenuate the SPN and Group II consisting of the filters that well preserve the SPN in the images. We further propose a CNN-based classifier to perform filter-oriented image categorization, aiming to exclude the images manipulated by the filters in Group I and thus improve the reliability of the SPN-based provenance analysis. The results on about 20, 000 images and 18 filters are very promising, with an accuracy higher than 96% in differentiating the filters in Group I and Group II.

Original language	English
Title of host publication	Data mining
Subtitle of host publication	16th Australasian conference, revised selected papers
Editors	Yanchang Zhao, Graco Warwick, David Stirling, Chang-Tsun Li, Yun Sing Koh, Rafiqul Islam, Zahidul Islam
Place of Publication	Singapore
Publisher	Springer-Verlag London Ltd.
Pages	372-383
Number of pages	12
ISBN (Electronic)	9789811366611
ISBN (Print)	9789811366604
DOIs	https://doi.org/10.1007/978-981-13-6661-1_29
Publication status	Published - Feb 2019
Event	The 16th Australasian Data Mining Conference - Charles Sturt University , Bathurst, Australia Duration: 28 Nov 2018 → 30 Nov 2018 https://web.archive.org/web/20181122224709/https://ausdm18.ausdm.org/ (Conference website) https://web.archive.org/web/20181202114109/http://ausdm18.ausdm.org/call-for-papers (Call for papers) https://web.archive.org/web/20181211153702/http://ausdm18.ausdm.org/program (Conference program)

Publication series

Name	Communications in Computer and Information Science
Publisher	Springer
Volume	996
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	The 16th Australasian Data Mining Conference
Country/Territory	Australia
City	Bathurst
Period	28/11/18 → 30/11/18
Other	The Australasian Data Mining Conference (AusDM) has established itself as the premier Australasian meeting for both practitioners and researchers in data mining. It is devoted to the art and science of intelligent analysis of (usually big) data sets for meaningful (and previously unknown) insights. This conference will enable the sharing and learning of research and progress in the local context and new breakthroughs in data mining algorithms and their applications across all industries.
Internet address	https://web.archive.org/web/20181122224709/https://ausdm18.ausdm.org/ (Conference website) https://web.archive.org/web/20181202114109/http://ausdm18.ausdm.org/call-for-papers (Call for papers) https://web.archive.org/web/20181211153702/http://ausdm18.ausdm.org/program (Conference program)

Access to Document

10.1007/978-981-13-6661-1_29

Cite this

Quan, Y., Lin, X., & Li, C. T. (2019). Provenance analysis for Instagram photos. In Y. Zhao, G. Warwick, D. Stirling, C.-T. Li, Y. S. Koh, R. Islam, & Z. Islam (Eds.), Data mining: 16th Australasian conference, revised selected papers (pp. 372-383). (Communications in Computer and Information Science; Vol. 996). Springer-Verlag London Ltd.. https://doi.org/10.1007/978-981-13-6661-1_29

Quan, Yijun ; Lin, Xufeng ; Li, Chang Tsun. / Provenance analysis for Instagram photos. Data mining: 16th Australasian conference, revised selected papers. editor / Yanchang Zhao ; Graco Warwick ; David Stirling ; Chang-Tsun Li ; Yun Sing Koh ; Rafiqul Islam ; Zahidul Islam. Singapore : Springer-Verlag London Ltd., 2019. pp. 372-383 (Communications in Computer and Information Science).

@inproceedings{6d38e97af7e14518ae29465a7c9e1a6c,

title = "Provenance analysis for Instagram photos",

abstract = "As a feasible device fingerprint, sensor pattern noise (SPN) has been proven to be effective in the provenance analysis of digital images. However, with the rise of social media, millions of images are being uploaded to and shared through social media sites every day. An image downloaded from social networks may have gone through a series of unknown image manipulations. Consequently, the trustworthiness of SPN has been challenged in the provenance analysis of the images downloaded from social media platforms. In this paper, we intend to investigate the effects of the pre-defined Instagram images filters on the SPN-based image provenance analysis. We identify two groups of filters that affect the SPN in quite different ways, with Group I consisting of the filters that severely attenuate the SPN and Group II consisting of the filters that well preserve the SPN in the images. We further propose a CNN-based classifier to perform filter-oriented image categorization, aiming to exclude the images manipulated by the filters in Group I and thus improve the reliability of the SPN-based provenance analysis. The results on about 20, 000 images and 18 filters are very promising, with an accuracy higher than 96% in differentiating the filters in Group I and Group II.",

keywords = "Digital image forensics, Provenance analysis, Sensor pattern noise, Social media",

author = "Yijun Quan and Xufeng Lin and Li, {Chang Tsun}",

note = "Includes bibliographical references.; The 16th Australasian Data Mining Conference ; Conference date: 28-11-2018 Through 30-11-2018",

year = "2019",

month = feb,

doi = "10.1007/978-981-13-6661-1_29",

language = "English",

isbn = "9789811366604",

series = "Communications in Computer and Information Science",

publisher = "Springer-Verlag London Ltd.",

pages = "372--383",

editor = "Yanchang Zhao and Graco Warwick and David Stirling and Chang-Tsun Li and Koh, {Yun Sing} and Rafiqul Islam and Zahidul Islam",

booktitle = "Data mining",

address = "Germany",

url = "https://web.archive.org/web/20181122224709/https://ausdm18.ausdm.org/, https://web.archive.org/web/20181202114109/http://ausdm18.ausdm.org/call-for-papers, https://web.archive.org/web/20181211153702/http://ausdm18.ausdm.org/program",

}

Quan, Y, Lin, X & Li, CT 2019, Provenance analysis for Instagram photos. in Y Zhao, G Warwick, D Stirling, C-T Li, YS Koh, R Islam & Z Islam (eds), Data mining: 16th Australasian conference, revised selected papers. Communications in Computer and Information Science, vol. 996, Springer-Verlag London Ltd., Singapore, pp. 372-383, The 16th Australasian Data Mining Conference, Bathurst, New South Wales, Australia, 28/11/18. https://doi.org/10.1007/978-981-13-6661-1_29

Provenance analysis for Instagram photos. / Quan, Yijun; Lin, Xufeng; Li, Chang Tsun.
Data mining: 16th Australasian conference, revised selected papers. ed. / Yanchang Zhao; Graco Warwick; David Stirling; Chang-Tsun Li; Yun Sing Koh; Rafiqul Islam; Zahidul Islam. Singapore: Springer-Verlag London Ltd., 2019. p. 372-383 (Communications in Computer and Information Science; Vol. 996).

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Provenance analysis for Instagram photos

AU - Quan, Yijun

AU - Lin, Xufeng

AU - Li, Chang Tsun

N1 - Includes bibliographical references.

PY - 2019/2

Y1 - 2019/2

N2 - As a feasible device fingerprint, sensor pattern noise (SPN) has been proven to be effective in the provenance analysis of digital images. However, with the rise of social media, millions of images are being uploaded to and shared through social media sites every day. An image downloaded from social networks may have gone through a series of unknown image manipulations. Consequently, the trustworthiness of SPN has been challenged in the provenance analysis of the images downloaded from social media platforms. In this paper, we intend to investigate the effects of the pre-defined Instagram images filters on the SPN-based image provenance analysis. We identify two groups of filters that affect the SPN in quite different ways, with Group I consisting of the filters that severely attenuate the SPN and Group II consisting of the filters that well preserve the SPN in the images. We further propose a CNN-based classifier to perform filter-oriented image categorization, aiming to exclude the images manipulated by the filters in Group I and thus improve the reliability of the SPN-based provenance analysis. The results on about 20, 000 images and 18 filters are very promising, with an accuracy higher than 96% in differentiating the filters in Group I and Group II.

AB - As a feasible device fingerprint, sensor pattern noise (SPN) has been proven to be effective in the provenance analysis of digital images. However, with the rise of social media, millions of images are being uploaded to and shared through social media sites every day. An image downloaded from social networks may have gone through a series of unknown image manipulations. Consequently, the trustworthiness of SPN has been challenged in the provenance analysis of the images downloaded from social media platforms. In this paper, we intend to investigate the effects of the pre-defined Instagram images filters on the SPN-based image provenance analysis. We identify two groups of filters that affect the SPN in quite different ways, with Group I consisting of the filters that severely attenuate the SPN and Group II consisting of the filters that well preserve the SPN in the images. We further propose a CNN-based classifier to perform filter-oriented image categorization, aiming to exclude the images manipulated by the filters in Group I and thus improve the reliability of the SPN-based provenance analysis. The results on about 20, 000 images and 18 filters are very promising, with an accuracy higher than 96% in differentiating the filters in Group I and Group II.

KW - Digital image forensics

KW - Provenance analysis

KW - Sensor pattern noise

KW - Social media

UR - http://www.scopus.com/inward/record.url?scp=85063548536&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063548536&partnerID=8YFLogxK

U2 - 10.1007/978-981-13-6661-1_29

DO - 10.1007/978-981-13-6661-1_29

M3 - Conference paper

AN - SCOPUS:85063548536

SN - 9789811366604

T3 - Communications in Computer and Information Science

SP - 372

EP - 383

BT - Data mining

A2 - Zhao, Yanchang

A2 - Warwick, Graco

A2 - Stirling, David

A2 - Li, Chang-Tsun

A2 - Koh, Yun Sing

A2 - Islam, Rafiqul

A2 - Islam, Zahidul

PB - Springer-Verlag London Ltd.

CY - Singapore

T2 - The 16th Australasian Data Mining Conference

Y2 - 28 November 2018 through 30 November 2018

ER -

Provenance analysis for Instagram photos

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this