Training Strategies and Data Augmentations in CNN-based DeepFake Video Detection

The fast and continuous growth in number and quality of deepfake videos calls for the development of reliable detection systems capable of automatically warning users on social media and on the Internet about the potential untruthfulness of such contents. While algorithms, software, and smartphone a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2020-11
Hauptverfasser: Bondi, Luca, Edoardo Daniele Cannas, Bestagini, Paolo, Tubaro, Stefano
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Bondi, Luca
Edoardo Daniele Cannas
Bestagini, Paolo
Tubaro, Stefano
description The fast and continuous growth in number and quality of deepfake videos calls for the development of reliable detection systems capable of automatically warning users on social media and on the Internet about the potential untruthfulness of such contents. While algorithms, software, and smartphone apps are getting better every day in generating manipulated videos and swapping faces, the accuracy of automated systems for face forgery detection in videos is still quite limited and generally biased toward the dataset used to design and train a specific detection system. In this paper we analyze how different training strategies and data augmentation techniques affect CNN-based deepfake detectors when training and testing on the same dataset or across different datasets.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2461164918</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2461164918</sourcerecordid><originalsourceid>FETCH-proquest_journals_24611649183</originalsourceid><addsrcrecordid>eNqNitEKgjAUQEcQJOU_DHoW3KZmj2FJTxIkvcotbzKrzXbn_2fQB_R0OJwzY4FUSkR5IuWChUR9HMcy28g0VQE71Q600abjZ-_AY6eROJiW78ED343dC40Hr60hrg0vqiq6AuHUEYcSHsgvukU7qcfbd1ux-R2ehOGPS7YuD3VxjAZn3yOSb3o7OjOlRiaZEFmyFbn67_oA-bQ-GQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2461164918</pqid></control><display><type>article</type><title>Training Strategies and Data Augmentations in CNN-based DeepFake Video Detection</title><source>Free E- Journals</source><creator>Bondi, Luca ; Edoardo Daniele Cannas ; Bestagini, Paolo ; Tubaro, Stefano</creator><creatorcontrib>Bondi, Luca ; Edoardo Daniele Cannas ; Bestagini, Paolo ; Tubaro, Stefano</creatorcontrib><description>The fast and continuous growth in number and quality of deepfake videos calls for the development of reliable detection systems capable of automatically warning users on social media and on the Internet about the potential untruthfulness of such contents. While algorithms, software, and smartphone apps are getting better every day in generating manipulated videos and swapping faces, the accuracy of automated systems for face forgery detection in videos is still quite limited and generally biased toward the dataset used to design and train a specific detection system. In this paper we analyze how different training strategies and data augmentation techniques affect CNN-based deepfake detectors when training and testing on the same dataset or across different datasets.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Applications programs ; Artificial neural networks ; Data augmentation ; Datasets ; Deception ; Digital media ; Smartphones ; Training ; Video</subject><ispartof>arXiv.org, 2020-11</ispartof><rights>2020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Bondi, Luca</creatorcontrib><creatorcontrib>Edoardo Daniele Cannas</creatorcontrib><creatorcontrib>Bestagini, Paolo</creatorcontrib><creatorcontrib>Tubaro, Stefano</creatorcontrib><title>Training Strategies and Data Augmentations in CNN-based DeepFake Video Detection</title><title>arXiv.org</title><description>The fast and continuous growth in number and quality of deepfake videos calls for the development of reliable detection systems capable of automatically warning users on social media and on the Internet about the potential untruthfulness of such contents. While algorithms, software, and smartphone apps are getting better every day in generating manipulated videos and swapping faces, the accuracy of automated systems for face forgery detection in videos is still quite limited and generally biased toward the dataset used to design and train a specific detection system. In this paper we analyze how different training strategies and data augmentation techniques affect CNN-based deepfake detectors when training and testing on the same dataset or across different datasets.</description><subject>Algorithms</subject><subject>Applications programs</subject><subject>Artificial neural networks</subject><subject>Data augmentation</subject><subject>Datasets</subject><subject>Deception</subject><subject>Digital media</subject><subject>Smartphones</subject><subject>Training</subject><subject>Video</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNitEKgjAUQEcQJOU_DHoW3KZmj2FJTxIkvcotbzKrzXbn_2fQB_R0OJwzY4FUSkR5IuWChUR9HMcy28g0VQE71Q600abjZ-_AY6eROJiW78ED343dC40Hr60hrg0vqiq6AuHUEYcSHsgvukU7qcfbd1ux-R2ehOGPS7YuD3VxjAZn3yOSb3o7OjOlRiaZEFmyFbn67_oA-bQ-GQ</recordid><startdate>20201116</startdate><enddate>20201116</enddate><creator>Bondi, Luca</creator><creator>Edoardo Daniele Cannas</creator><creator>Bestagini, Paolo</creator><creator>Tubaro, Stefano</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20201116</creationdate><title>Training Strategies and Data Augmentations in CNN-based DeepFake Video Detection</title><author>Bondi, Luca ; Edoardo Daniele Cannas ; Bestagini, Paolo ; Tubaro, Stefano</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24611649183</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Algorithms</topic><topic>Applications programs</topic><topic>Artificial neural networks</topic><topic>Data augmentation</topic><topic>Datasets</topic><topic>Deception</topic><topic>Digital media</topic><topic>Smartphones</topic><topic>Training</topic><topic>Video</topic><toplevel>online_resources</toplevel><creatorcontrib>Bondi, Luca</creatorcontrib><creatorcontrib>Edoardo Daniele Cannas</creatorcontrib><creatorcontrib>Bestagini, Paolo</creatorcontrib><creatorcontrib>Tubaro, Stefano</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Bondi, Luca</au><au>Edoardo Daniele Cannas</au><au>Bestagini, Paolo</au><au>Tubaro, Stefano</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Training Strategies and Data Augmentations in CNN-based DeepFake Video Detection</atitle><jtitle>arXiv.org</jtitle><date>2020-11-16</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>The fast and continuous growth in number and quality of deepfake videos calls for the development of reliable detection systems capable of automatically warning users on social media and on the Internet about the potential untruthfulness of such contents. While algorithms, software, and smartphone apps are getting better every day in generating manipulated videos and swapping faces, the accuracy of automated systems for face forgery detection in videos is still quite limited and generally biased toward the dataset used to design and train a specific detection system. In this paper we analyze how different training strategies and data augmentation techniques affect CNN-based deepfake detectors when training and testing on the same dataset or across different datasets.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2020-11
issn 2331-8422
language eng
recordid cdi_proquest_journals_2461164918
source Free E- Journals
subjects Algorithms
Applications programs
Artificial neural networks
Data augmentation
Datasets
Deception
Digital media
Smartphones
Training
Video
title Training Strategies and Data Augmentations in CNN-based DeepFake Video Detection
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T02%3A07%3A59IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Training%20Strategies%20and%20Data%20Augmentations%20in%20CNN-based%20DeepFake%20Video%20Detection&rft.jtitle=arXiv.org&rft.au=Bondi,%20Luca&rft.date=2020-11-16&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2461164918%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2461164918&rft_id=info:pmid/&rfr_iscdi=true