Collusion-Resistant Audio Fingerprinting System in the Modulated Complex Lapped Transform Domain

Jose Juan Garcia-Hernandez,Rene Cumplido,Claudia Feregrino-Uribe,Randen Lee Patterson

doi:10.1371/journal.pone.0065985

Jose Juan Garcia-Hernandez, Rene Cumplido + Show 2 more

Open Access

https://doi.org/10.1371/journal.pone.0065985

Copy DOI

Abstract

Collusion-resistant fingerprinting paradigm seems to be a practical solution to the piracy problem as it allows media owners to detect any unauthorized copy and trace it back to the dishonest users. Despite the billionaire losses in the music industry, most of the collusion-resistant fingerprinting systems are devoted to digital images and very few to audio signals. In this paper, state-of-the-art collusion-resistant fingerprinting ideas are extended to audio signals and the corresponding parameters and operation conditions are proposed. Moreover, in order to carry out fingerprint detection using just a fraction of the pirate audio clip, block-based embedding and its corresponding detector is proposed. Extensive simulations show the robustness of the proposed system against average collusion attack. Moreover, by using an efficient Fast Fourier Transform core and standard computer machines it is shown that the proposed system is suitable for real-world scenarios.

Highlights

In the Information Technology era, expansion of the Internet service together with the rapid advance of high capacity storage systems facilitated the fast and perfect copy of digital content
The proposed audio fingerprinting system is evaluated under averaging collusion attacks
The probability of false detection is set to 10{6 for both group (Pfag ) and user ID detection (Pfau ) procedures, as this is a typical value in audio spread spectrum-based watermarking systems [11]

Summary

Introduction

In the Information Technology era, expansion of the Internet service together with the rapid advance of high capacity storage systems facilitated the fast and perfect copy of digital content. One possible solution to this problem is the fingerprinting paradigm, where, a unique signature (which identifies to the legal user) known as a digital fingerprint is hidden using a watermarking technique into the content previously to distribution. Digital fingerprinting, which is a watermarking application, has the capacity of identifying illegal users by extracting the fingerprint of a suspicious copy. A typical attack in fingerprinting systems is the collusion attack, where a group of users combine their copies in order to remove the original fingerprint. If a sufficient number of copies are combined, the noise produced by the collusion attack can disable/confuse the fingerprint detector and prevent the content owner from identifying the illegal users. It is necessary to design collusion-resistant fingerprints that can identify the greatest number of colluders involved in a pirate copy

Methods

Results

Conclusion