Detection and classification of double compressed MP3 audio tracks

Authors:
Tiziano Bianchi;Alessia De Rosa;Marco Fontani;Giovanni Rocciolo;Alessandro Piva
Affiliations:
Politecnico di Torino, Torino, Italy;National Inter-University Consortium for Telecommunications, Firenze, Italy;University of Siena, Siena, Italy;University of Florence, Firenze, Italy;University of Florence, Firenze, Italy
Venue:
Proceedings of the first ACM workshop on Information hiding and multimedia security
Year:
2013

Citing 7
Cited 0

Introduction to Information Retrieval

Introduction to Information Retrieval
Detecting digital audio forgeries by checking frame offsets

Proceedings of the 10th ACM workshop on Multimedia and security
Fast, automatic and fine-grained tampered JPEG image detection via DCT coefficient analysis

Pattern Recognition
Defeating fake-quality MP3

Proceedings of the 11th ACM workshop on Multimedia and security
Revealing real quality of double compressed MP3 audio

Proceedings of the international conference on Multimedia
Statistical tools for digital forensics

IH'04 Proceedings of the 6th international conference on Information Hiding
Exposing MP3 audio forgeries using frame offsets

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) - Special Issue on Multimedia Security

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a method to detect the presence of double compression in a MP3 audio file is proposed. By exploiting the effect of double compression in the statistical properties of quantized MDCT coefficients, a single measure is derived to decide if a MP3 file is single compressed or it has been double compressed and also to devise the bit-rate of the first compression. Experimental results confirm the performance of the detector, mainly when the bit-rate of the second compression is higher than the bit-rate of the first one.