Seam-carving based anonymization against image & video source attribution

Sevinç Bayram, Husrev T. Sencar, Nasir D. Memon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

As image source attribution techniques have become significantly sophisticated and are now becoming commonplace, there is a growing need for capabilities to anonymize images and videos. Focusing on the photo response non-uniformity noise pattern based sensor fingerprinting technique, this work evaluates the effectiveness of well-established seam carving method to defend against sensor fingerprint matching. We consider ways in which seam-carving based anonymization can be countered and propose enhancements over conventional seam carving method. Our results show that applying geometrical distortion in addition to seam carving will make counter attack very ineffective both in terms of computational complexity and accuracy.

Original languageEnglish (US)
Title of host publication2013 IEEE International Workshop on Multimedia Signal Processing, MMSP 2013
Pages272-277
Number of pages6
DOIs
StatePublished - 2013
Event2013 IEEE 15th International Workshop on Multimedia Signal Processing, MMSP 2013 - Pula, Sardinia, Italy
Duration: Sep 30 2013Oct 2 2013

Other

Other2013 IEEE 15th International Workshop on Multimedia Signal Processing, MMSP 2013
CountryItaly
CityPula, Sardinia
Period9/30/1310/2/13

Fingerprint

Sensors
Computational complexity

ASJC Scopus subject areas

  • Signal Processing

Cite this

Bayram, S., Sencar, H. T., & Memon, N. D. (2013). Seam-carving based anonymization against image & video source attribution. In 2013 IEEE International Workshop on Multimedia Signal Processing, MMSP 2013 (pp. 272-277). [6659300] https://doi.org/10.1109/MMSP.2013.6659300

Seam-carving based anonymization against image & video source attribution. / Bayram, Sevinç; Sencar, Husrev T.; Memon, Nasir D.

2013 IEEE International Workshop on Multimedia Signal Processing, MMSP 2013. 2013. p. 272-277 6659300.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bayram, S, Sencar, HT & Memon, ND 2013, Seam-carving based anonymization against image & video source attribution. in 2013 IEEE International Workshop on Multimedia Signal Processing, MMSP 2013., 6659300, pp. 272-277, 2013 IEEE 15th International Workshop on Multimedia Signal Processing, MMSP 2013, Pula, Sardinia, Italy, 9/30/13. https://doi.org/10.1109/MMSP.2013.6659300
Bayram S, Sencar HT, Memon ND. Seam-carving based anonymization against image & video source attribution. In 2013 IEEE International Workshop on Multimedia Signal Processing, MMSP 2013. 2013. p. 272-277. 6659300 https://doi.org/10.1109/MMSP.2013.6659300
Bayram, Sevinç ; Sencar, Husrev T. ; Memon, Nasir D. / Seam-carving based anonymization against image & video source attribution. 2013 IEEE International Workshop on Multimedia Signal Processing, MMSP 2013. 2013. pp. 272-277
@inproceedings{fe0cc7b63d75424fa6e5f584b583266b,
title = "Seam-carving based anonymization against image & video source attribution",
abstract = "As image source attribution techniques have become significantly sophisticated and are now becoming commonplace, there is a growing need for capabilities to anonymize images and videos. Focusing on the photo response non-uniformity noise pattern based sensor fingerprinting technique, this work evaluates the effectiveness of well-established seam carving method to defend against sensor fingerprint matching. We consider ways in which seam-carving based anonymization can be countered and propose enhancements over conventional seam carving method. Our results show that applying geometrical distortion in addition to seam carving will make counter attack very ineffective both in terms of computational complexity and accuracy.",
author = "Sevin{\cc} Bayram and Sencar, {Husrev T.} and Memon, {Nasir D.}",
year = "2013",
doi = "10.1109/MMSP.2013.6659300",
language = "English (US)",
isbn = "9781479901258",
pages = "272--277",
booktitle = "2013 IEEE International Workshop on Multimedia Signal Processing, MMSP 2013",

}

TY - GEN

T1 - Seam-carving based anonymization against image & video source attribution

AU - Bayram, Sevinç

AU - Sencar, Husrev T.

AU - Memon, Nasir D.

PY - 2013

Y1 - 2013

N2 - As image source attribution techniques have become significantly sophisticated and are now becoming commonplace, there is a growing need for capabilities to anonymize images and videos. Focusing on the photo response non-uniformity noise pattern based sensor fingerprinting technique, this work evaluates the effectiveness of well-established seam carving method to defend against sensor fingerprint matching. We consider ways in which seam-carving based anonymization can be countered and propose enhancements over conventional seam carving method. Our results show that applying geometrical distortion in addition to seam carving will make counter attack very ineffective both in terms of computational complexity and accuracy.

AB - As image source attribution techniques have become significantly sophisticated and are now becoming commonplace, there is a growing need for capabilities to anonymize images and videos. Focusing on the photo response non-uniformity noise pattern based sensor fingerprinting technique, this work evaluates the effectiveness of well-established seam carving method to defend against sensor fingerprint matching. We consider ways in which seam-carving based anonymization can be countered and propose enhancements over conventional seam carving method. Our results show that applying geometrical distortion in addition to seam carving will make counter attack very ineffective both in terms of computational complexity and accuracy.

UR - http://www.scopus.com/inward/record.url?scp=84892536728&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84892536728&partnerID=8YFLogxK

U2 - 10.1109/MMSP.2013.6659300

DO - 10.1109/MMSP.2013.6659300

M3 - Conference contribution

AN - SCOPUS:84892536728

SN - 9781479901258

SP - 272

EP - 277

BT - 2013 IEEE International Workshop on Multimedia Signal Processing, MMSP 2013

ER -