A Novel Detection Algorithm of Double MP3
Compression
Pengfei Ma, Rangding Wang
1
, Diqun Yan, Chao Jin
Abstract. MP3 is the most widely used audio format nowadays in our daily life,
while MP3 audio often be forged by an audio forger for their own benefits in some
significant events, which will cause double MP3 compression. In this paper, it is
the first time to calculate the statistical frequency of Huffman code table index,
and a support vector machine is applied for classification to detect double MP3
compression. Experimental results demonstrate that the proposed method has low
complexity and high accuracy, also the blank with the high bitrate in double MP3
compression detection is made up.
Keywords: Huffman table index
double MP3 compression
high bitrate
1 Introduction
With the development of the multimedia information technology, audio, video,
images and other multimedia information industry penetrate into every corner of
our society, and bring us great convenience. However, everything have two sides,
some non-professionals can modify the multimedia information without leaving
obvious traces by using the cheap or free multimedia editing software. Although
most people manipulate the multimedia information in order to make the multi-
media become more perfect, if some criminals maliciously modified the multime-
dia information for their own interests to harm the harmonious society, the conse-
quences would be disastrous [1]. For example, the tampered audio can be taken as
evidence in court, which will result in the opposite outcome of the trial; false-
quality audios spreading widely on the market, may infringe the copyright of for-
mal business; a speech which conveys orders in the military being tampered, can
cause military conflict and so on. Therefore, more and more people begin to pay
attention to the security issues of multimedia information. The process of com-
pressed audio tampering must take double audio compression [2-4]. As the current
Rangding Wang ()
College of Information Science and Engineering, Ningbo University, Ningbo, China
wangrangding@nbu.edu.cn
剩余7页未读，继续阅读
资源评论
