sesa 15(6): e1

Research Article

A Method to Detect AAC Audio Forgery

Download505 downloads
  • @ARTICLE{10.4108/icst.mobimedia.2015.259141,
        author={Qingzhong Liu and Andrew Sung and Lei Chen and Ming Yang and Zhongxue Chen and Yanxin Liu and Jing Zhang},
        title={A Method to Detect AAC Audio Forgery},
        journal={EAI Endorsed Transactions on Security and Safety},
        volume={2},
        number={6},
        publisher={EAI},
        journal_a={SESA},
        year={2015},
        month={8},
        keywords={forgery detection; audio forensics; aac; same bitrate},
        doi={10.4108/icst.mobimedia.2015.259141}
    }
    
  • Qingzhong Liu
    Andrew Sung
    Lei Chen
    Ming Yang
    Zhongxue Chen
    Yanxin Liu
    Jing Zhang
    Year: 2015
    A Method to Detect AAC Audio Forgery
    SESA
    EAI
    DOI: 10.4108/icst.mobimedia.2015.259141
Qingzhong Liu,*, Andrew Sung1, Lei Chen2, Ming Yang3, Zhongxue Chen4, Yanxin Liu2, Jing Zhang5
  • 1: University of Southern Mississippi
  • 2: Sam Houston State University
  • 3: Kennesaw State University
  • 4: Indiana University
  • 5: Tianjin University
*Contact email: liu@shsu.edu

Abstract

Advanced Audio Coding (AAC), a standardized lossy compression scheme for digital audio, which was designed to be the successor of the MP3 format, generally achieves better sound quality than MP3 at similar bit rates. While AAC is also the default or standard audio format for many devices and AAC audio files may be presented as important digital evidences, the authentication of the audio files is highly needed but relatively missing. In this paper, we propose a scheme to expose tampered AAC audio streams that are encoded at the same encoding bit-rate. Specifically, we design a shift-recompression based method to retrieve the differential features between the re-encoded audio stream at each shifting and original audio stream, learning classifier is employed to recognize different patterns of differential features of the doctored forgery files and original (untouched) audio files. Experimental results show that our approach is very promising and effective to detect the forgery of the same encoding bit-rate on AAC audio streams. Our study also shows that shift recompression-based differential analysis is very effective for detection of the MP3 forgery at the same bit rate.