Provenance filtering for multimedia phylogeny

A. Pinto; D. Moreira; A. Bharati; J. Brogan; K. Bowyer; P. Flynn; W. Scheirer; A. Rocha

doi:10.1109/ICIP.2017.8296532

Provenance filtering for multimedia phylogeny

A. Pinto, D. Moreira, A. Bharati, J. Brogan, K. Bowyer, P. Flynn, W. Scheirer, A. Rocha

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

12 Scopus citations

Abstract

Departing from traditional digital forensics modeling, which seeks to analyze single objects in isolation, multimedia phylogeny analyzes the evolutionary processes that influence digital objects and collections over time. One of its integral pieces is provenance filtering, which consists of searching a potentially large pool of objects for the most related ones with respect to a given query, in terms of possible ancestors (donors or contributors) and descendants. In this paper, we propose a two-tiered provenance filtering approach to find all the potential images that might have contributed to the creation process of a given query q. In our solution, the first (coarse) tier aims to find the most likely 'host' images - the major donor or background - contributing to a composite/doctored image. The search is then refined in the second tier, in which we search for more specific (potentially small) parts of the query that might have been extracted from other images and spliced into the query image. Experimental results with a dataset containing more than a million images show that the two-tiered solution underpinned by the context of the query is highly useful for solving this difficult task.

Original language	English
Title of host publication	2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
Publisher	IEEE Computer Society
Pages	1502-1506
Number of pages	5
ISBN (Electronic)	9781509021758
DOIs	https://doi.org/10.1109/ICIP.2017.8296532
State	Published - Jul 2 2017
Externally published	Yes
Event	24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China Duration: Sep 17 2017 → Sep 20 2017

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2017-September
ISSN (Print)	1522-4880

Conference

Conference	24th IEEE International Conference on Image Processing, ICIP 2017
Country/Territory	China
City	Beijing
Period	09/17/17 → 09/20/17

Funding

This material is based on research sponsored by DARPA and Air Force Research Laboratory (AFRL) under agreement number FA8750-16-2-0173. Hardware support was generously provided by the NVIDIA Corporation. We also thank the financial support of FAPESP (Grant #2015/19222-9), CAPES (DeepEyes Grant) and CNPq (Grant #304472/2015-8).

Keywords

Multimedia Phylogeny
Phylogeny Graph
Provenance Context Incorporation
Provenance Filtering

Access to Document

10.1109/ICIP.2017.8296532

Cite this

Pinto, A., Moreira, D., Bharati, A., Brogan, J., Bowyer, K., Flynn, P., Scheirer, W., & Rocha, A. (2017). Provenance filtering for multimedia phylogeny. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings (pp. 1502-1506). (Proceedings - International Conference on Image Processing, ICIP; Vol. 2017-September). IEEE Computer Society. https://doi.org/10.1109/ICIP.2017.8296532

@inproceedings{cf9d906ca59643f0b13bf610caa32b10,

title = "Provenance filtering for multimedia phylogeny",

abstract = "Departing from traditional digital forensics modeling, which seeks to analyze single objects in isolation, multimedia phylogeny analyzes the evolutionary processes that influence digital objects and collections over time. One of its integral pieces is provenance filtering, which consists of searching a potentially large pool of objects for the most related ones with respect to a given query, in terms of possible ancestors (donors or contributors) and descendants. In this paper, we propose a two-tiered provenance filtering approach to find all the potential images that might have contributed to the creation process of a given query q. In our solution, the first (coarse) tier aims to find the most likely 'host' images - the major donor or background - contributing to a composite/doctored image. The search is then refined in the second tier, in which we search for more specific (potentially small) parts of the query that might have been extracted from other images and spliced into the query image. Experimental results with a dataset containing more than a million images show that the two-tiered solution underpinned by the context of the query is highly useful for solving this difficult task.",

keywords = "Multimedia Phylogeny, Phylogeny Graph, Provenance Context Incorporation, Provenance Filtering",

author = "A. Pinto and D. Moreira and A. Bharati and J. Brogan and K. Bowyer and P. Flynn and W. Scheirer and A. Rocha",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 24th IEEE International Conference on Image Processing, ICIP 2017 ; Conference date: 17-09-2017 Through 20-09-2017",

year = "2017",

month = jul,

day = "2",

doi = "10.1109/ICIP.2017.8296532",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "1502--1506",

booktitle = "2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings",

}

Pinto, A, Moreira, D, Bharati, A, Brogan, J, Bowyer, K, Flynn, P, Scheirer, W & Rocha, A 2017, Provenance filtering for multimedia phylogeny. in 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Proceedings - International Conference on Image Processing, ICIP, vol. 2017-September, IEEE Computer Society, pp. 1502-1506, 24th IEEE International Conference on Image Processing, ICIP 2017, Beijing, China, 09/17/17. https://doi.org/10.1109/ICIP.2017.8296532

Provenance filtering for multimedia phylogeny. / Pinto, A.; Moreira, D.; Bharati, A. et al.
2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. IEEE Computer Society, 2017. p. 1502-1506 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2017-September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Provenance filtering for multimedia phylogeny

AU - Pinto, A.

AU - Moreira, D.

AU - Bharati, A.

AU - Brogan, J.

AU - Bowyer, K.

AU - Flynn, P.

AU - Scheirer, W.

AU - Rocha, A.

PY - 2017/7/2

Y1 - 2017/7/2

N2 - Departing from traditional digital forensics modeling, which seeks to analyze single objects in isolation, multimedia phylogeny analyzes the evolutionary processes that influence digital objects and collections over time. One of its integral pieces is provenance filtering, which consists of searching a potentially large pool of objects for the most related ones with respect to a given query, in terms of possible ancestors (donors or contributors) and descendants. In this paper, we propose a two-tiered provenance filtering approach to find all the potential images that might have contributed to the creation process of a given query q. In our solution, the first (coarse) tier aims to find the most likely 'host' images - the major donor or background - contributing to a composite/doctored image. The search is then refined in the second tier, in which we search for more specific (potentially small) parts of the query that might have been extracted from other images and spliced into the query image. Experimental results with a dataset containing more than a million images show that the two-tiered solution underpinned by the context of the query is highly useful for solving this difficult task.

AB - Departing from traditional digital forensics modeling, which seeks to analyze single objects in isolation, multimedia phylogeny analyzes the evolutionary processes that influence digital objects and collections over time. One of its integral pieces is provenance filtering, which consists of searching a potentially large pool of objects for the most related ones with respect to a given query, in terms of possible ancestors (donors or contributors) and descendants. In this paper, we propose a two-tiered provenance filtering approach to find all the potential images that might have contributed to the creation process of a given query q. In our solution, the first (coarse) tier aims to find the most likely 'host' images - the major donor or background - contributing to a composite/doctored image. The search is then refined in the second tier, in which we search for more specific (potentially small) parts of the query that might have been extracted from other images and spliced into the query image. Experimental results with a dataset containing more than a million images show that the two-tiered solution underpinned by the context of the query is highly useful for solving this difficult task.

KW - Multimedia Phylogeny

KW - Phylogeny Graph

KW - Provenance Context Incorporation

KW - Provenance Filtering

UR - http://www.scopus.com/inward/record.url?scp=85045316942&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2017.8296532

DO - 10.1109/ICIP.2017.8296532

M3 - Conference contribution

AN - SCOPUS:85045316942

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 1502

EP - 1506

BT - 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings

PB - IEEE Computer Society

T2 - 24th IEEE International Conference on Image Processing, ICIP 2017

Y2 - 17 September 2017 through 20 September 2017

ER -

Provenance filtering for multimedia phylogeny

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this