{"id":14128677,"url":"https://github.com/Charleswyt/tf_audio_steganalysis","last_synced_at":"2025-08-03T23:32:10.710Z","repository":{"id":29050815,"uuid":"117548221","full_name":"Charleswyt/tf_audio_steganalysis","owner":"Charleswyt","description":"Audio steganalysis  with tensorflow.","archived":false,"fork":false,"pushed_at":"2024-04-09T03:02:13.000Z","size":57835,"stargazers_count":358,"open_issues_count":3,"forks_count":52,"subscribers_count":6,"default_branch":"master","last_synced_at":"2024-08-16T16:22:50.123Z","etag":null,"topics":["audio","cnn","deep-learning","mp3","steganalysis","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Charleswyt.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2018-01-15T13:22:04.000Z","updated_at":"2024-08-12T19:35:31.000Z","dependencies_parsed_at":"2024-01-12T19:47:26.172Z","dependency_job_id":"d1265ff2-edd6-4458-9cce-575a725a6dc7","html_url":"https://github.com/Charleswyt/tf_audio_steganalysis","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Charleswyt%2Ftf_audio_steganalysis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Charleswyt%2Ftf_audio_steganalysis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Charleswyt%2Ftf_audio_steganalysis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Charleswyt%2Ftf_audio_steganalysis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Charleswyt","download_url":"https://codeload.github.com/Charleswyt/tf_audio_steganalysis/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":228571844,"owners_count":17938772,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["audio","cnn","deep-learning","mp3","steganalysis","tensorflow"],"created_at":"2024-08-15T16:02:02.352Z","updated_at":"2024-12-07T06:31:36.107Z","avatar_url":"https://github.com/Charleswyt.png","language":"Python","funding_links":[],"categories":["Python","3. [↑](#-content) Cryptography"],"sub_categories":["[↑](#-content) 3.3 Steganalysis"],"readme":"# Audio Steganalysis with Deep Learning\n\n@ Author: **Yuntao Wang (Charles_wyt)** \u003cbr\u003e\n@ Email: ~~wangyuntao2@iie.ac.cn (deactivation)~~ charles_wyt@163.com \u003cbr\u003e\nHope we have a happy communication.\n\n---\nThis project is a **tensorflow** implementation of our recent work, and you can design your own networks through the platform.\n+ [CNN-based Steganalysis of MP3 Steganography in the Entropy\nCode Domain](https://github.com/Charleswyt/tf_audio_steganalysis/tree/master/papers/CNN-based%20Steganalysis%20of%20MP3%20Steganography%20in%20the%20Entropy%20Code%20Domain) [[IH\u0026MMSec](https://www.ihmmsec.org) 2018, Best Paper Award] \u003cbr\u003e\n**[[Paper (ACM)](https://dl.acm.org/citation.cfm?id=3206011)]** **[[Paper (pdf)](http://www.media-security.net/?p=809)]** **[[Dataset](https://github.com/Charleswyt/tf_audio_steganalysis/tree/master/papers)]**\n+ [RHFCN: Fully CNN-based Steganalysis of MP3 with Rich High-Pass Filtering](https://github.com/Charleswyt/tf_audio_steganalysis/tree/master/papers/RHFCN%20-%20Fully%20CNN-based%20Steganalysis%20of%20MP3%20with%20Rich%20High-Pass%20Filtering) [[ICASSP](https://2019.ieeeicassp.org) 2019] \u003cbr\u003e\n**[[Paper (IEEE)](https://ieeexplore.ieee.org/document/8683626)]** **[[Paper (pdf)](http://www.media-security.net/?p=969)]** **[[Dataset](https://github.com/Charleswyt/tf_audio_steganalysis/tree/master/papers)]**\n+ [MP3 Steganalysis based on Joint Point-wise and Block-wise CSorrelations](https://github.com/Charleswyt/tf_audio_steganalysis/tree/master/papers/RHFCN%20-%20Fully%20CNN-based%20Steganalysis%20of%20MP3%20with%20Rich%20High-Pass%20Filtering) [[Information Sciences](https://www.sciencedirect.com/journal/information-sciences)] \u003cbr\u003e\n**[[Paper (Elsevier)](https://www.sciencedirect.com/science/article/pii/S0020025519310047)]** **[[Repositories](https://github.com/Charleswyt/audio_steganalysis_ml)]**\n\n## Necessary Packages\ntensorflow-gpu==1.3 or later, numpy, pandas, matplotlib, scikit-image, scikit-learn, filetype, [virtualenv](https://charleswyt.github.io/2018/09/06/python%E8%99%9A%E6%8B%9F%E7%8E%AF%E5%A2%83%E5%AE%89%E8%A3%85%E5%8F%8A%E4%BD%BF%E7%94%A8/), [librosa](http://librosa.github.io/librosa/core.html) (depends on **[FFmpeg](http://www.ffmpeg.org/download.html)**)\n\nYou can use the command, **pip install -r requirements.txt**, to install all necessary packages mentioned above. If you don't want to change or break your original version of tensorflow, you can use [**virtualenv**](https://charleswyt.github.io/2018/09/06/python%E8%99%9A%E6%8B%9F%E7%8E%AF%E5%A2%83%E5%AE%89%E8%A3%85%E5%8F%8A%E4%BD%BF%E7%94%A8/) to create a new python runtime environment.\n\n## How to Use\n1. Install [**Python3.x**](https://www.python.org/) or [**Anaconda**](https://repo.continuum.io/archive/), and add the installation directory into the environment variable (recommand python3.5).\n2. **GPU** runtime environment [**configure**](https://blog.csdn.net/yhaolpz/article/details/71375762?locationNum=14\u0026fps=1) for the network training (**optional**).\n3. Install all dependent packages mentioned above (open **[setup](https://github.com/Charleswyt/tf_audio_steganalysis/tree/master/setup)/requirements.txt**, and input \"**pip install -r requirements**\" into your terminal window).\n4. **Run** the code as the [**example**](https://github.com/Charleswyt/tf_audio_steganalysis/tree/master/src/config_file) shows.\n5. Use [**tensorboard**](http://wiki.jikexueyuan.com/project/tensorflow-zh/how_tos/graph_viz.html) to visualize the training process such as the **accuracy** and **loss curve** of the training. The command is \"**tensorboard --logdir=/path of log**\".\n6. If you want to design your own network based on this project, there is a brief [**instruction**](https://github.com/Charleswyt/tf_audio_steganalysis/tree/master/src/networks/network_design.md) for you.\n7. All our sourcecode is writen with [**Pycharm**](https://github.com/Charleswyt/tf_audio_steganalysis/blob/master/setup/pycharm.md), and the **hard wrap** is setted as **180**. If your setting of hard wrap is less than 180, there will be warnings shwon in the IDE.\n\n## Files Description\nID      |   File                    |   Function\n:-      |   :-                      |    :-\n1       |   audio_samples           |   some audio samples\n2       |   data_processing         |   dataset build, tools which are used for QMDCT coefficients extraction and so on\n3       |   jupyter                 |   a folder for debug with jupyter\n4       |   papers                  |   the paper, presentation, dataset and brief introduction of our recent work\n5       |   setup                   |   setup and configuration\n6       |   src                     |   source code\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCharleswyt%2Ftf_audio_steganalysis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FCharleswyt%2Ftf_audio_steganalysis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCharleswyt%2Ftf_audio_steganalysis/lists"}