An efficient algorithm for double compressed AAC audio detection

Abstract

As a new generation of compression encoding standard, MPEG-2/4 Advanced Audio Coding (AAC) would be a widely-used audio format in the near future. However, these AAC audios often be forged by audio forgers for their own benefits in some significant events, which will cause double AAC compression. In this paper, the probability values and Markov features based on the Huffman codebook indexes of AAC audio were constructed and an efficient algorithm is proposed to detect double compression. Experimental results demonstrate that our method has high detection accuracy and low computational complexity. To the best of our knowledge, it is the first time to apply double compression detection to AAC audio forensics.

AAC Double Compression Audio Detection Algorithm Based on the Difference of Scale Factor

“…It can be seen from Table 5 that the detection rate of the AAC audio Jin feature with low bit rate transcoding to high bit rate is high, which is not much different from that of the scale factor difference and occurrence probability difference in the algorithm of this paper. However, the detection effect between the same code rate in the literature [15] is poor. The algorithm in this paper solves similar problems and increases the detection rate of the same-rate compressed audio by nearly 20 percentage points.…”

“…In order to fully evaluate the performance of the algorithm proposed in this paper, this section reconstructs the features of Jin et al [15] and conducts comparative experiments. The specific method of Jin feature construction is to use the Huffman code table to use the difference in single compression and double compression of AAC audio and take the probability of occurrence of the Huffman code table index as the first feature.…”

“…The algorithm in this paper solves similar problems and increases the detection rate of the same-rate compressed audio by nearly 20 percentage points. For a better comparison with this algorithm, Table 6 shows the comparison of F1 values between this algorithm and literature [15]. The AAC and MP3 codec are highly similar in principle.…”

“…In advanced audio coding (AAC) audio double compression detection, Jin et al [15] combined the probability of occurrence of the Huffman code table index with its Markov one-step transition probability and used LIBSVM to classify single and double compressed AAC audio. Its detection rate of compressed audio at the same code rate is low.…”

“…Comparison between[15] and the Feature f usion of this algorithm-FAAC (%). Comparison between[15] and the Feature f usion F1 of this algorithm-FAAC (%).…”