A. Hafeez, H. Malik, and K. Mahmood, “Performance of Blind Microphone Recognition Algorithms in the Presence of Anti-Forensic Attacks,” in Proc. AES Conference: 2017 AES International Conference on Audio Forensics, Jun. 2017, Paper 4-2. [Online]. Available: https://aes.org/publications/elibrary-page/?id=18749
Hafeez A, Malik H, Mahmood K. Performance of Blind Microphone Recognition Algorithms in the Presence of Anti-Forensic Attacks. In: AES Conference: 2017 AES International Conference on Audio Forensics. Audio Engineering Society; 2017. Paper 4-2. Available from: https://aes.org/publications/elibrary-page/?id=18749
@inproceedings{Hafeez2017_18749,
author = {Hafeez, Azeem and Malik, Hafiz and Mahmood, Khalid},
title = {{Performance of Blind Microphone Recognition Algorithms in the Presence of Anti-Forensic Attacks}},
booktitle = {AES Conference: 2017 AES International Conference on Audio Forensics},
note = {Paper 4-2},
year = {2017},
month = jun,
publisher = {Audio Engineering Society},
url = {https://aes.org/publications/elibrary-page/?id=18749}
}
TY - CPAPER
TI - Performance of Blind Microphone Recognition Algorithms in the Presence of Anti-Forensic Attacks
AU - Hafeez, Azeem
AU - Malik, Hafiz
AU - Mahmood, Khalid
T2 - AES Conference: 2017 AES International Conference on Audio Forensics
M1 - Paper 4-2
PY - 2017
DA - 2017/06/06
UR - https://aes.org/publications/elibrary-page/?id=18749
PB - Audio Engineering Society
LA - en
AB - Audio recording system leaves its characteristic artifacts in the recordings made through it which are used to link an audio recording to “the” microphone used. Microphone recognition method is a process in which microphone is recognized from the audio recorded using the characteristic artifacts. This paper focuses on the performance analysis of microphone identification algorithms in the presence of splicing attack. Statistical pattern recognition based method for blind detection method for microphone identification is used for this study. Performance of selected method is evaluated both in the presence and in the absence of splicing attack. Experimental results indicate that the selected method fail to detect any forgeries less than 20% of the length of the recording.
ER -
