Audio Steganalysis Dataset
The steganography and steganalysis of audio, especially compressed audio, have drawn increasing attention in recent years, and various algorithms are proposed. However, there is no standard public dataset for us to verify the efficiency of each proposed algorithm. Therefore, to promote the study field, we construct a dataset including 33038 stereo WAV audio clips with a sampling rate of 44.1 kHz and duration of 10s. And, all audio files are from the Internet through data crawling, which is for a better simulation of a real detection environment. The dataset is used for MP3 steganalysis at this stage. We provide corresponding MP3 encoder, LAME, and steganographic encoder, HCM, EECS and so on, which is developed based on LAME. What's more, some useful python scripts are supplied for samples make in batch. The dataset is still expanding, and we will include AAC, AMR and other audio formats in the future.
Keywords: Audio, MP3, Steganalysis, Steganography
- The secret message files for embedding. secret_message.zip (5.72 MB)
- MP3 audio encoder and steganographic encoder. encoder.zip (2.73 MB)
- A tiny dataset including 1000 WAV audio files. wav_10s demo.zip (1.58 GB)
- A small dataset including 5000 WAV audio files. wav_10s_lite.zip (7.88 GB)
- A middle dataset including 10000 WAV audio files. wav_10s_middle.zip (15.65 GB)