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
Python package for analyzing sensor-collected human motion data

Python package for analyzing sensor-collected human motion data

Simon Ho 71 Nov 05, 2022
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
Bearsql allows you to query pandas dataframe with sql syntax.

Bearsql adds sql syntax on pandas dataframe. It uses duckdb to speedup the pandas processing and as the sql engine

14 Jun 22, 2022
Data cleaning tools for Business analysis

Datacleaning datacleaning tools for Business analysis This program is made for Vicky's work. You can use it, too. 数据清洗 该数据清洗工具是为了商业分析 这个程序是为了Vicky的工作而

Lin Jian 3 Nov 16, 2021
An implementation of the largeVis algorithm for visualizing large, high-dimensional datasets, for R

largeVis This is an implementation of the largeVis algorithm described in (https://arxiv.org/abs/1602.00370). It also incorporates: A very fast algori

336 May 25, 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 simple and efficient tool to parallelize Pandas operations on all available CPUs

Pandaral·lel Without parallelization With parallelization Installation $ pip install pandarallel [--upgrade] [--user] Requirements On Windows, Pandara

Manu NALEPA 2.8k Dec 31, 2022
Analyzing Covid-19 Outbreaks in Ontario

My group and I took Covid-19 outbreak statistics from ontario, and analyzed them to find different patterns and future predictions for the virus

Vishwaajeeth Kamalakkannan 0 Jan 20, 2022
Python package for processing UC module spectral data.

UC Module Python Package How To Install clone repo. cd UC-module pip install . How to Use uc.module.UC(measurment=str, dark=str, reference=str, heade

Nicolai Haaber Junge 1 Oct 20, 2021
Leverage Twitter API v2 to analyze tweet metrics such as impressions and profile clicks over time.

Tweetmetric Tweetmetric allows you to track various metrics on your most recent tweets, such as impressions, retweets and clicks on your profile. The

Mathis HAMMEL 29 Oct 18, 2022
For making Tagtog annotation into csv dataset

tagtog_relation_extraction for making Tagtog annotation into csv dataset How to Use On Tagtog 1. Go to Project Downloads 2. Download all documents,

hyeong 4 Dec 28, 2021
Creating a statistical model to predict 10 year treasury yields

Predicting 10-Year Treasury Yields Intitially, I wanted to see if the volatility in the stock market, represented by the VIX index (data source), had

10 Oct 27, 2021
First steps with Python in Life Sciences

First steps with Python in Life Sciences This course material is part of the "First Steps with Python in Life Science" three-day course of SIB-trainin

SIB Swiss Institute of Bioinformatics 22 Jan 08, 2023
Pandas on AWS - Easy integration with Athena, Glue, Redshift, Timestream, QuickSight, Chime, CloudWatchLogs, DynamoDB, EMR, SecretManager, PostgreSQL, MySQL, SQLServer and S3 (Parquet, CSV, JSON and EXCEL).

AWS Data Wrangler Pandas on AWS Easy integration with Athena, Glue, Redshift, Timestream, QuickSight, Chime, CloudWatchLogs, DynamoDB, EMR, SecretMana

Amazon Web Services - Labs 3.3k Jan 04, 2023
Desafio proposto pela IGTI em seu bootcamp de Cloud Data Engineer

Desafio Modulo 4 - Cloud Data Engineer Bootcamp - IGTI Objetivos Criar infraestrutura como código Utuilizando um cluster Kubernetes na Azure Ingestão

Otacilio Filho 4 Jan 23, 2022
Pyspark project that able to do joins on the spark data frames.

SPARK JOINS This project is to perform inner, all outer joins and semi joins. create_df.py: load_data.py : helps to put data into Spark data frames. d

Joshua 1 Dec 14, 2021
Mining the Stack Overflow Developer Survey

Mining the Stack Overflow Developer Survey A prototype data mining application to compare the accuracy of decision tree and random forest regression m

1 Nov 16, 2021
Approximate Nearest Neighbor Search for Sparse Data in Python!

Approximate Nearest Neighbor Search for Sparse Data in Python! This library is well suited to finding nearest neighbors in sparse, high dimensional spaces (like text documents).

Meta Research 906 Jan 01, 2023
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
A lightweight, hub-and-spoke dashboard for multi-account Data Science projects

A lightweight, hub-and-spoke dashboard for cross-account Data Science Projects Introduction Modern Data Science environments often involve many indepe

AWS Samples 3 Oct 30, 2021