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...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2020-11 |
---|---|
Hauptverfasser: | , , , |
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 & 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 |