WaveFake: A Data Set to Facilitate Audio DeepFake Detection

Related tags

Data AnalysisWaveFake
Overview

WaveFake: A Data Set to Facilitate Audio DeepFake Detection

logo

This is the code repository for our NeurIPS 2021 (Track on Datasets and Benchmarks) paper WaveFake.

Deep generative modeling has the potential to cause significant harm to society. Recognizing this threat, a magnitude of research into detecting so-called "Deepfakes" has emerged. This research most often focuses on the image domain, while studies exploring generated audio signals have - so far - been neglected. In this paper, we aim to narrow this gap. We present a novel data set, for which we collected ten sample sets from six different network architectures, spanning two languages. We analyze the frequency statistics comprehensively, discovering subtle differences between the architectures, specifically among the higher frequencies. Additionally, to facilitate further development of detection methods, we implemented three different classifiers adopted from the signal processing community to give practitioners a baseline to compare against. In a first evaluation, we already discovered significant trade-offs between the different approaches. Neural network-based approaches performed better on average, but more traditional models proved to be more robust.

Dataset & Pre-trained Models

You can find our dataset on zenodo and we also provide pre-trained models.

Setup

You can install all needed dependencies by running:

pip install -r requirements.txt

RawNet2 Model

For consistency, we use the RawNet2 model provided by the ASVSpoof 2021 challenge. Please download the model specifications here and place it under dfadetect/models as raw_net2.py.

Statistics & Plots

To recreate the plots/statistics of the paper, use:

python statistics.py -h

usage: statistics.py [-h] [--amount AMOUNT] [--no-stats] [DATASETS ...]

positional arguments:
  DATASETS              Path to datasets. The first entry is assumed to be the referrence one. Specified as follows <path,name>

optional arguments:
  -h, --help            show this help message and exit
  --amount AMOUNT, -a AMOUNT
                        Amount of files to concider.
  --no-stats, -s        Do not compute stats, only plots.

Example

python statistics.py /path/to/reference/data,ReferenceDataName /path/to/generated/data,GeneratedDataName -a 10000

Training models

You can use the training script as follows:

python train_models.py -h

usage: train_models.py [-h] [--amount AMOUNT] [--clusters CLUSTERS] [--batch_size BATCH_SIZE] [--epochs EPOCHS] [--retraining RETRAINING] [--ckpt CKPT] [--use_em] [--raw_net] [--cuda] [--lfcc] [--debug] [--verbose] REAL FAKE

positional arguments:
  REAL                  Directory containing real data.
  FAKE                  Directory containing fake data.

optional arguments:
  -h, --help            show this help message and exit
  --amount AMOUNT, -a AMOUNT
                        Amount of files to load from each directory (default: None - all).
  --clusters CLUSTERS, -k CLUSTERS
                        The amount of clusters to learn (default: 128).
  --batch_size BATCH_SIZE, -b BATCH_SIZE
                        Batch size (default: 8).
  --epochs EPOCHS, -e EPOCHS
                        Epochs (default: 5).
  --retraining RETRAINING, -r RETRAINING
                        Retraining tries (default: 10).
  --ckpt CKPT           Checkpoint directory (default: trained_models).
  --use_em              Use EM version?
  --raw_net             Train raw net version?
  --cuda, -c            Use cuda?
  --lfcc, -l            Use LFCC instead of MFCC?
  --debug, -d           Only use minimal amount of files?
  --verbose, -v         Display debug information?

Example

To train all EM-GMMs use:

python train_models.py /data/LJSpeech-1.1/wavs /data/generated_audio -k 128 -v --use_em --epochs 100

Evaluation

For evaluation you can use the evaluate_models script:

python evaluate_models.p -h

usage: evaluate_models.py [-h] [--output OUTPUT] [--clusters CLUSTERS] [--amount AMOUNT] [--raw_net] [--debug] [--cuda] REAL FAKE MODELS

positional arguments:
  REAL                  Directory containing real data.
  FAKE                  Directory containing fake data.
  MODELS                Directory containing model checkpoints.

optional arguments:
  -h, --help            show this help message and exit
  --output OUTPUT, -o OUTPUT
                        Output file name.
  --clusters CLUSTERS, -k CLUSTERS
                        The amount of clusters to learn (default: 128).
  --amount AMOUNT, -a AMOUNT
                        Amount of files to load from each directory (default: None - all).
  --raw_net, -r         RawNet models?
  --debug, -d           Only use minimal amount of files?
  --cuda, -c            Use cuda?

Example

python evaluate_models.py /data/LJSpeech-1.1/wavs /data/generated_audio trained_models/lfcc/em

Make sure to move the out-of-distribution models to a seperate directory first!

Attribution

We provide a script to attribute the GMM models:

python attribute.py -h

usage: attribute.py [-h] [--clusters CLUSTERS] [--steps STEPS] [--blur] FILE REAL_MODEL FAKE_MODEL

positional arguments:
  FILE                  Audio sample to attribute.
  REAL_MODEL            Real model to attribute.
  FAKE_MODEL            Fake Model to attribute.

optional arguments:
  -h, --help            show this help message and exit
  --clusters CLUSTERS, -k CLUSTERS
                        The amount of clusters to learn (default: 128).
  --steps STEPS, -m STEPS
                        Amount of steps for integrated gradients.
  --blur, -b            Compute BlurIG instead.

Example

python attribute.py /data/LJSpeech-1.1/wavs/LJ008-0217.wav path/to/real/model.pth path/to/fake/model.pth

BibTeX

When you cite our work feel free to use the following bibtex entry:

@inproceedings{
  frank2021wavefake,
  title={{WaveFake: A Data Set to Facilitate Audio Deepfake Detection}},
  author={Joel Frank and Lea Sch{\"o}nherr},
  booktitle={Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
  year={2021},
}
Owner
Chair for Sys­tems Se­cu­ri­ty
Chair for Sys­tems Se­cu­ri­ty
A model checker for verifying properties in epistemic models

Epistemic Model Checker This is a model checker for verifying properties in epistemic models. The goal of the model checker is to check for Pluralisti

Thomas Träff 2 Dec 22, 2021
Evidence enables analysts to deliver a polished business intelligence system using SQL and markdown.

Evidence enables analysts to deliver a polished business intelligence system using SQL and markdown

915 Dec 26, 2022
A data structure that extends pyspark.sql.DataFrame with metadata information.

MetaFrame A data structure that extends pyspark.sql.DataFrame with metadata info

Invent Analytics 8 Feb 15, 2022
Repositori untuk menyimpan material Long Course STMKGxHMGI tentang Geophysical Python for Seismic Data Analysis

Long Course "Geophysical Python for Seismic Data Analysis" Instruktur: Dr.rer.nat. Wiwit Suryanto, M.Si Dipersiapkan oleh: Anang Sahroni Waktu: Sesi 1

Anang Sahroni 0 Dec 04, 2021
SNV calling pipeline developed explicitly to process individual or trio vcf files obtained from Illumina based pipeline (grch37/grch38).

SNV Pipeline SNV calling pipeline developed explicitly to process individual or trio vcf files obtained from Illumina based pipeline (grch37/grch38).

East Genomics 1 Nov 02, 2021
Numerical Analysis toolkit centred around PDEs, for demonstration and understanding purposes not production

Numerics Numerical Analysis toolkit centred around PDEs, for demonstration and understanding purposes not production Use procedure: Initialise a new i

George Whittle 1 Nov 13, 2021
This mini project showcase how to build and debug Apache Spark application using Python

Spark app can't be debugged using normal procedure. This mini project showcase how to build and debug Apache Spark application using Python programming language. There are also options to run Spark a

Denny Imanuel 1 Dec 29, 2021
Basis Set Format Converter

Basis Set Format Converter Repository for the online tool that allows you to enter a basis set in the form of text input for a variety of Quantum Chem

Manas Sharma 3 Jun 27, 2022
Clean and reusable data-sciency notebooks.

KPACUBO KPACUBO is a set Jupyter notebooks focused on the best practices in both software development and data science, namely, code reuse, explicit d

Matvey Morozov 1 Jan 28, 2022
My first Python project is a simple Mad Libs program.

Python CLI Mad Libs Game My first Python project is a simple Mad Libs program. Mad Libs is a phrasal template word game created by Leonard Stern and R

Carson Johnson 1 Dec 10, 2021
VHub - An API that permits uploading of vulnerability datasets and return of the serialized data

VHub - An API that permits uploading of vulnerability datasets and return of the serialized data

André Rodrigues 2 Feb 14, 2022
Convert tables stored as images to an usable .csv file

Convert an image of numbers to a .csv file This Python program aims to convert images of array numbers to corresponding .csv files. It uses OpenCV for

711 Dec 26, 2022
The official repository for ROOT: analyzing, storing and visualizing big data, scientifically

About The ROOT system provides a set of OO frameworks with all the functionality needed to handle and analyze large amounts of data in a very efficien

ROOT 2k Dec 29, 2022
Full ELT process on GCP environment.

Rent Houses Germany - GCP Pipeline Project: The goal of the project is to extract data about house rentals in Germany, store, process and analyze it u

Felipe Demenech Vasconcelos 2 Jan 20, 2022
VevestaX is an open source Python package for ML Engineers and Data Scientists.

VevestaX Track failed and successful experiments as well as features. VevestaX is an open source Python package for ML Engineers and Data Scientists.

Vevesta 24 Dec 14, 2022
Two phase pipeline + StreamlitTwo phase pipeline + Streamlit

Two phase pipeline + Streamlit This is an example project that demonstrates how to create a pipeline that consists of two phases of execution. In betw

Rick Lamers 1 Nov 17, 2021
Code for the DH project "Dhimmis & Muslims – Analysing Multireligious Spaces in the Medieval Muslim World"

Damast This repository contains code developed for the digital humanities project "Dhimmis & Muslims – Analysing Multireligious Spaces in the Medieval

University of Stuttgart Visualization Research Center 2 Jul 01, 2022
Retail-Sim is python package to easily create synthetic dataset of retaile store.

Retailer's Sale Data Simulation Retail-Sim is python package to easily create synthetic dataset of retaile store. Simulation Model Simulator consists

Corca AI 7 Sep 30, 2022
CINECA molecular dynamics tutorial set

High Performance Molecular Dynamics Logging into CINECA's computer systems To logon to the M100 system use the following command from an SSH client ss

J. W. Dell 0 Mar 13, 2022
Renato 214 Jan 02, 2023