Blind Detection of Copy-Move Forgery in Digital Audio Forensics

Muhammad Imran, Zulfiqar Ali, Sheikh Tahir Bakhsh, Sheeraz Akram

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Although copy-move forgery is one of the most common fabrication techniques, blind detection of such tampering in digital audio is mostly unexplored. Unlike active techniques, blind forgery detection is challenging, because it does not embed a watermark or signature in an audio that is unknown in most of the real-life scenarios. Therefore, forgery localization becomes more challenging, especially when using blind methods. In this paper, we propose a novel method for blind detection and localization of copy-move forgery. One of the most crucial steps in the proposed method is a voice activity detection (VAD) module for investigating audio recordings to detect and localize the forgery. The VAD module is equally vital for the development of the copy-move forgery database, wherein audio samples are generated by using the recordings of various types of microphones. We employ a chaotic theory to copy and move the text in generated forged recordings to ensure forgery localization at any place in a recording. The VAD module is responsible for the extraction of words in a forged audio, these words are analyzed by applying a 1-D local binary pattern operator. This operator provides the patterns of extracted words in the form of histograms. The forged parts (copy and move text) have similar histograms. An accuracy of 96.59% is achieved, the proposed method is deemed robust against noise.

LanguageEnglish
Pages12843-12855
Number of pages13
JournalIEEE Access
Volume5
DOIs
Publication statusPublished - 21 Jun 2017

Fingerprint

Audio recordings
Microphones
Fabrication

Keywords

  • audio forgery
  • authentication
  • blind detection
  • copy-move forgery
  • Digital multimedia forensics

Cite this

Imran, Muhammad ; Ali, Zulfiqar ; Bakhsh, Sheikh Tahir ; Akram, Sheeraz. / Blind Detection of Copy-Move Forgery in Digital Audio Forensics. In: IEEE Access. 2017 ; Vol. 5. pp. 12843-12855.
@article{8e5f635f0ded483792330a4d6b7610a6,
title = "Blind Detection of Copy-Move Forgery in Digital Audio Forensics",
abstract = "Although copy-move forgery is one of the most common fabrication techniques, blind detection of such tampering in digital audio is mostly unexplored. Unlike active techniques, blind forgery detection is challenging, because it does not embed a watermark or signature in an audio that is unknown in most of the real-life scenarios. Therefore, forgery localization becomes more challenging, especially when using blind methods. In this paper, we propose a novel method for blind detection and localization of copy-move forgery. One of the most crucial steps in the proposed method is a voice activity detection (VAD) module for investigating audio recordings to detect and localize the forgery. The VAD module is equally vital for the development of the copy-move forgery database, wherein audio samples are generated by using the recordings of various types of microphones. We employ a chaotic theory to copy and move the text in generated forged recordings to ensure forgery localization at any place in a recording. The VAD module is responsible for the extraction of words in a forged audio, these words are analyzed by applying a 1-D local binary pattern operator. This operator provides the patterns of extracted words in the form of histograms. The forged parts (copy and move text) have similar histograms. An accuracy of 96.59{\%} is achieved, the proposed method is deemed robust against noise.",
keywords = "audio forgery, authentication, blind detection, copy-move forgery, Digital multimedia forensics",
author = "Muhammad Imran and Zulfiqar Ali and Bakhsh, {Sheikh Tahir} and Sheeraz Akram",
year = "2017",
month = "6",
day = "21",
doi = "10.1109/ACCESS.2017.2717842",
language = "English",
volume = "5",
pages = "12843--12855",
journal = "IEEE Access",
issn = "2169-3536",

}

Blind Detection of Copy-Move Forgery in Digital Audio Forensics. / Imran, Muhammad; Ali, Zulfiqar; Bakhsh, Sheikh Tahir; Akram, Sheeraz.

In: IEEE Access, Vol. 5, 21.06.2017, p. 12843-12855.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Blind Detection of Copy-Move Forgery in Digital Audio Forensics

AU - Imran, Muhammad

AU - Ali, Zulfiqar

AU - Bakhsh, Sheikh Tahir

AU - Akram, Sheeraz

PY - 2017/6/21

Y1 - 2017/6/21

N2 - Although copy-move forgery is one of the most common fabrication techniques, blind detection of such tampering in digital audio is mostly unexplored. Unlike active techniques, blind forgery detection is challenging, because it does not embed a watermark or signature in an audio that is unknown in most of the real-life scenarios. Therefore, forgery localization becomes more challenging, especially when using blind methods. In this paper, we propose a novel method for blind detection and localization of copy-move forgery. One of the most crucial steps in the proposed method is a voice activity detection (VAD) module for investigating audio recordings to detect and localize the forgery. The VAD module is equally vital for the development of the copy-move forgery database, wherein audio samples are generated by using the recordings of various types of microphones. We employ a chaotic theory to copy and move the text in generated forged recordings to ensure forgery localization at any place in a recording. The VAD module is responsible for the extraction of words in a forged audio, these words are analyzed by applying a 1-D local binary pattern operator. This operator provides the patterns of extracted words in the form of histograms. The forged parts (copy and move text) have similar histograms. An accuracy of 96.59% is achieved, the proposed method is deemed robust against noise.

AB - Although copy-move forgery is one of the most common fabrication techniques, blind detection of such tampering in digital audio is mostly unexplored. Unlike active techniques, blind forgery detection is challenging, because it does not embed a watermark or signature in an audio that is unknown in most of the real-life scenarios. Therefore, forgery localization becomes more challenging, especially when using blind methods. In this paper, we propose a novel method for blind detection and localization of copy-move forgery. One of the most crucial steps in the proposed method is a voice activity detection (VAD) module for investigating audio recordings to detect and localize the forgery. The VAD module is equally vital for the development of the copy-move forgery database, wherein audio samples are generated by using the recordings of various types of microphones. We employ a chaotic theory to copy and move the text in generated forged recordings to ensure forgery localization at any place in a recording. The VAD module is responsible for the extraction of words in a forged audio, these words are analyzed by applying a 1-D local binary pattern operator. This operator provides the patterns of extracted words in the form of histograms. The forged parts (copy and move text) have similar histograms. An accuracy of 96.59% is achieved, the proposed method is deemed robust against noise.

KW - audio forgery

KW - authentication

KW - blind detection

KW - copy-move forgery

KW - Digital multimedia forensics

UR - http://www.scopus.com/inward/record.url?scp=85021821243&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2017.2717842

DO - 10.1109/ACCESS.2017.2717842

M3 - Article

VL - 5

SP - 12843

EP - 12855

JO - IEEE Access

T2 - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -