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
MEAD: A Large-scale Audio-visual Dataset for Emotional Talking-face Generation [ECCV2020]

MEAD: A Large-scale Audio-visual Dataset for Emotional Talking-face Generation [ECCV2020] by Kaisiyuan Wang, Qianyi Wu, Linsen Song, Zhuoqian Yang, Wa

112 Dec 28, 2022
A probabilistic programming library for Bayesian deep learning, generative models, based on Tensorflow

ZhuSuan is a Python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and

Tsinghua Machine Learning Group 2.2k Dec 28, 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
API>local_db>AWS_RDS - Disclaimer! All data used is for educational purposes only.

APIlocal_dbAWS_RDS Disclaimer! All data used is for educational purposes only. ETL pipeline diagram. Aim of project By creating a fully working pipe

0 Apr 25, 2022
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
ped-crash-techvol: Texas Ped Crash Tech Volume Pack

ped-crash-techvol: Texas Ped Crash Tech Volume Pack In conjunction with the Final Report "Identifying Risk Factors that Lead to Increase in Fatal Pede

Network Modeling Center; Center for Transportation Research; The University of Texas at Austin 2 Sep 28, 2022
Intercepting proxy + analysis toolkit for Second Life compatible virtual worlds

Hippolyzer Hippolyzer is a revival of Linden Lab's PyOGP library targeting modern Python 3, with a focus on debugging issues in Second Life-compatible

Salad Dais 6 Sep 01, 2022
PipeChain is a utility library for creating functional pipelines.

PipeChain Motivation PipeChain is a utility library for creating functional pipelines. Let's start with a motivating example. We have a list of Austra

Michael Milton 2 Aug 07, 2022
A simplified prototype for an as-built tracking database with API

Asbuilt_Trax A simplified prototype for an as-built tracking database with API The purpose of this project is to: Model a database that tracks constru

Ryan Pemberton 1 Jan 31, 2022
AptaMat is a simple script which aims to measure differences between DNA or RNA secondary structures.

AptaMAT Purpose AptaMat is a simple script which aims to measure differences between DNA or RNA secondary structures. The method is based on the compa

GEC UTC 3 Nov 03, 2022
Shot notebooks resuming the main functions of GeoPandas

Shot notebooks resuming the main functions of GeoPandas, 2 notebooks written as Exercises to apply these functions.

1 Jan 12, 2022
Multiple Pairwise Comparisons (Post Hoc) Tests in Python

scikit-posthocs is a Python package that provides post hoc tests for pairwise multiple comparisons that are usually performed in statistical data anal

Maksim Terpilowski 264 Dec 30, 2022
Program that predicts the NBA mvp based on data from previous years.

NBA MVP Predictor A machine learning model using RandomForest Regression that predicts NBA MVP's using player data. Explore the docs » View Demo · Rep

Muhammad Rabee 1 Jan 21, 2022
A multi-platform GUI for bit-based analysis, processing, and visualization

A multi-platform GUI for bit-based analysis, processing, and visualization

Mahlet 529 Dec 19, 2022
Snakemake workflow for converting FASTQ files to self-contained CRAM files with maximum lossless compression.

Snakemake workflow: name A Snakemake workflow for description Usage The usage of this workflow is described in the Snakemake Workflow Catalog. If

Algorithms for reproducible bioinformatics (Koesterlab) 1 Dec 16, 2021
Python ELT Studio, an application for building ELT (and ETL) data flows.

The Python Extract, Load, Transform Studio is an application for performing ELT (and ETL) tasks. Under the hood the application consists of a two parts.

Schlerp 55 Nov 18, 2022
A tool to compare differences between dataframes and create a differences report in Excel

similarpanda A module to check for differences between pandas Dataframes, and generate a report in Excel format. This is helpful in a workplace settin

Andre Pretorius 9 Sep 15, 2022
Hue Editor: Open source SQL Query Assistant for Databases/Warehouses

Hue Editor: Open source SQL Query Assistant for Databases/Warehouses

Cloudera 759 Jan 07, 2023
Pypeln is a simple yet powerful Python library for creating concurrent data pipelines.

Pypeln Pypeln (pronounced as "pypeline") is a simple yet powerful Python library for creating concurrent data pipelines. Main Features Simple: Pypeln

Cristian Garcia 1.4k Dec 31, 2022