Why Do Facial Deepfake Detectors Fail?
Recent rapid advancements in deepfake technology have allowed the creation of highly realistic fake media, such as video, image, and audio. These materials pose significant challenges to human authentication, such as impersonation, misinformation, or even a threat to national security. To keep pace...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2023-09 |
|---|---|
| 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 | Le, Binh Shahroz Tariq Alsharif Abuadbba Moore, Kristen Woo, Simon |
| description | Recent rapid advancements in deepfake technology have allowed the creation of highly realistic fake media, such as video, image, and audio. These materials pose significant challenges to human authentication, such as impersonation, misinformation, or even a threat to national security. To keep pace with these rapid advancements, several deepfake detection algorithms have been proposed, leading to an ongoing arms race between deepfake creators and deepfake detectors. Nevertheless, these detectors are often unreliable and frequently fail to detect deepfakes. This study highlights the challenges they face in detecting deepfakes, including (1) the pre-processing pipeline of artifacts and (2) the fact that generators of new, unseen deepfake samples have not been considered when building the defense models. Our work sheds light on the need for further research and development in this field to create more robust and reliable detectors. |
| doi_str_mv | 10.48550/arxiv.2302.13156 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2302_13156</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2780574174</sourcerecordid><originalsourceid>FETCH-LOGICAL-a956-5456b78e6bb2cd997019d484f4c8822c4072a5049381d688ca26fd4e885a68b63</originalsourceid><addsrcrecordid>eNotj0FLw0AUhBdBsNT-AE8GBG-Ju2_f2305ibRWhYKXgsew2WwwNZq6ScX--8bW0wzMMMwnxJWSGTKRvHPxt_nJQEvIlFZkzsQEtFYpI8CFmPX9RkoJxgKRnojbt_d9suiSpfONa5NFCNvafYTRDMEPXezHpGnvL8V57do-zP51KtbLx_X8OV29Pr3MH1apy8mkhGRKy8GUJfgqz61UeYWMNXpmAI_SgiOJuWZVGWbvwNQVBmZyhkujp-L6NHuEKLax-XRxX_zBFEeYsXFzamxj970L_VBsul38Gj8VYFmSRWVRHwDm4UkF</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2780574174</pqid></control><display><type>article</type><title>Why Do Facial Deepfake Detectors Fail?</title><source>World Web Journals</source><source>arXiv.org</source><creator>Le, Binh ; Shahroz Tariq ; Alsharif Abuadbba ; Moore, Kristen ; Woo, Simon</creator><creatorcontrib>Le, Binh ; Shahroz Tariq ; Alsharif Abuadbba ; Moore, Kristen ; Woo, Simon</creatorcontrib><description>Recent rapid advancements in deepfake technology have allowed the creation of highly realistic fake media, such as video, image, and audio. These materials pose significant challenges to human authentication, such as impersonation, misinformation, or even a threat to national security. To keep pace with these rapid advancements, several deepfake detection algorithms have been proposed, leading to an ongoing arms race between deepfake creators and deepfake detectors. Nevertheless, these detectors are often unreliable and frequently fail to detect deepfakes. This study highlights the challenges they face in detecting deepfakes, including (1) the pre-processing pipeline of artifacts and (2) the fact that generators of new, unseen deepfake samples have not been considered when building the defense models. Our work sheds light on the need for further research and development in this field to create more robust and reliable detectors.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2302.13156</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Computer Science - Cryptography and Security ; Computer Science - Learning ; Deception ; Detectors ; R&D ; Research & development</subject><ispartof>arXiv.org, 2023-09</ispartof><rights>2023. 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><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,780,881,27902</link.rule.ids><backlink>$$Uhttps://doi.org/10.1145/3595353.3595882$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.2302.13156$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Le, Binh</creatorcontrib><creatorcontrib>Shahroz Tariq</creatorcontrib><creatorcontrib>Alsharif Abuadbba</creatorcontrib><creatorcontrib>Moore, Kristen</creatorcontrib><creatorcontrib>Woo, Simon</creatorcontrib><title>Why Do Facial Deepfake Detectors Fail?</title><title>arXiv.org</title><description>Recent rapid advancements in deepfake technology have allowed the creation of highly realistic fake media, such as video, image, and audio. These materials pose significant challenges to human authentication, such as impersonation, misinformation, or even a threat to national security. To keep pace with these rapid advancements, several deepfake detection algorithms have been proposed, leading to an ongoing arms race between deepfake creators and deepfake detectors. Nevertheless, these detectors are often unreliable and frequently fail to detect deepfakes. This study highlights the challenges they face in detecting deepfakes, including (1) the pre-processing pipeline of artifacts and (2) the fact that generators of new, unseen deepfake samples have not been considered when building the defense models. Our work sheds light on the need for further research and development in this field to create more robust and reliable detectors.</description><subject>Algorithms</subject><subject>Computer Science - Cryptography and Security</subject><subject>Computer Science - Learning</subject><subject>Deception</subject><subject>Detectors</subject><subject>R&D</subject><subject>Research & development</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><sourceid>GOX</sourceid><recordid>eNotj0FLw0AUhBdBsNT-AE8GBG-Ju2_f2305ibRWhYKXgsew2WwwNZq6ScX--8bW0wzMMMwnxJWSGTKRvHPxt_nJQEvIlFZkzsQEtFYpI8CFmPX9RkoJxgKRnojbt_d9suiSpfONa5NFCNvafYTRDMEPXezHpGnvL8V57do-zP51KtbLx_X8OV29Pr3MH1apy8mkhGRKy8GUJfgqz61UeYWMNXpmAI_SgiOJuWZVGWbvwNQVBmZyhkujp-L6NHuEKLax-XRxX_zBFEeYsXFzamxj970L_VBsul38Gj8VYFmSRWVRHwDm4UkF</recordid><startdate>20230910</startdate><enddate>20230910</enddate><creator>Le, Binh</creator><creator>Shahroz Tariq</creator><creator>Alsharif Abuadbba</creator><creator>Moore, Kristen</creator><creator>Woo, Simon</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>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230910</creationdate><title>Why Do Facial Deepfake Detectors Fail?</title><author>Le, Binh ; Shahroz Tariq ; Alsharif Abuadbba ; Moore, Kristen ; Woo, Simon</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a956-5456b78e6bb2cd997019d484f4c8822c4072a5049381d688ca26fd4e885a68b63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Computer Science - Cryptography and Security</topic><topic>Computer Science - Learning</topic><topic>Deception</topic><topic>Detectors</topic><topic>R&D</topic><topic>Research & development</topic><toplevel>online_resources</toplevel><creatorcontrib>Le, Binh</creatorcontrib><creatorcontrib>Shahroz Tariq</creatorcontrib><creatorcontrib>Alsharif Abuadbba</creatorcontrib><creatorcontrib>Moore, Kristen</creatorcontrib><creatorcontrib>Woo, Simon</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Database (Proquest)</collection><collection>ProQuest Central (Alumni)</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</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>ProQuest 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>Engineering collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Le, Binh</au><au>Shahroz Tariq</au><au>Alsharif Abuadbba</au><au>Moore, Kristen</au><au>Woo, Simon</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Why Do Facial Deepfake Detectors Fail?</atitle><jtitle>arXiv.org</jtitle><date>2023-09-10</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Recent rapid advancements in deepfake technology have allowed the creation of highly realistic fake media, such as video, image, and audio. These materials pose significant challenges to human authentication, such as impersonation, misinformation, or even a threat to national security. To keep pace with these rapid advancements, several deepfake detection algorithms have been proposed, leading to an ongoing arms race between deepfake creators and deepfake detectors. Nevertheless, these detectors are often unreliable and frequently fail to detect deepfakes. This study highlights the challenges they face in detecting deepfakes, including (1) the pre-processing pipeline of artifacts and (2) the fact that generators of new, unseen deepfake samples have not been considered when building the defense models. Our work sheds light on the need for further research and development in this field to create more robust and reliable detectors.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2302.13156</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2023-09 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_arxiv_primary_2302_13156 |
| source | World Web Journals; arXiv.org |
| subjects | Algorithms Computer Science - Cryptography and Security Computer Science - Learning Deception Detectors R&D Research & development |
| title | Why Do Facial Deepfake Detectors Fail? |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-01T09%3A25%3A55IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Why%20Do%20Facial%20Deepfake%20Detectors%20Fail?&rft.jtitle=arXiv.org&rft.au=Le,%20Binh&rft.date=2023-09-10&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2302.13156&rft_dat=%3Cproquest_arxiv%3E2780574174%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2780574174&rft_id=info:pmid/&rfr_iscdi=true |