Identification of Social-Media Platform of Videos through the Use of Shared Features
Videos have become a powerful tool for spreading illegal content such as military propaganda, revenge porn, or bullying through social networks. To counter these illegal activities, it has become essential to try new methods to verify the origin of videos from these platforms. However, collecting da...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/7/8/140 |
| _version_ | 1797523344361259008 |
|---|---|
| author | Luca Maiano Irene Amerini Lorenzo Ricciardi Celsi Aris Anagnostopoulos |
| author_facet | Luca Maiano Irene Amerini Lorenzo Ricciardi Celsi Aris Anagnostopoulos |
| author_sort | Luca Maiano |
| collection | DOAJ |
| description | Videos have become a powerful tool for spreading illegal content such as military propaganda, revenge porn, or bullying through social networks. To counter these illegal activities, it has become essential to try new methods to verify the origin of videos from these platforms. However, collecting datasets large enough to train neural networks for this task has become difficult because of the privacy regulations that have been enacted in recent years. To mitigate this limitation, in this work we propose two different solutions based on transfer learning and multitask learning to determine whether a video has been uploaded from or downloaded to a specific social platform through the use of shared features with images trained on the same task. By transferring features from the shallowest to the deepest levels of the network from the image task to videos, we measure the amount of information shared between these two tasks. Then, we introduce a model based on multitask learning, which learns from both tasks simultaneously. The promising experimental results show, in particular, the effectiveness of the multitask approach. According to our knowledge, this is the first work that addresses the problem of social media platform identification of videos through the use of shared features. |
| first_indexed | 2024-03-10T08:41:37Z |
| format | Article |
| id | doaj.art-1314eb0d4f804ccf986a876fd05f0530 |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-10T08:41:37Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-1314eb0d4f804ccf986a876fd05f05302023-11-22T08:13:58ZengMDPI AGJournal of Imaging2313-433X2021-08-017814010.3390/jimaging7080140Identification of Social-Media Platform of Videos through the Use of Shared FeaturesLuca Maiano0Irene Amerini1Lorenzo Ricciardi Celsi2Aris Anagnostopoulos3Department of Computer, Control and Management Engineering, Sapienza University of Rome, via Ariosto, 25, 00185 Rome, ItalyDepartment of Computer, Control and Management Engineering, Sapienza University of Rome, via Ariosto, 25, 00185 Rome, ItalyElis Innovation Hub, via Sandro Sandri 81, 00159 Rome, ItalyDepartment of Computer, Control and Management Engineering, Sapienza University of Rome, via Ariosto, 25, 00185 Rome, ItalyVideos have become a powerful tool for spreading illegal content such as military propaganda, revenge porn, or bullying through social networks. To counter these illegal activities, it has become essential to try new methods to verify the origin of videos from these platforms. However, collecting datasets large enough to train neural networks for this task has become difficult because of the privacy regulations that have been enacted in recent years. To mitigate this limitation, in this work we propose two different solutions based on transfer learning and multitask learning to determine whether a video has been uploaded from or downloaded to a specific social platform through the use of shared features with images trained on the same task. By transferring features from the shallowest to the deepest levels of the network from the image task to videos, we measure the amount of information shared between these two tasks. Then, we introduce a model based on multitask learning, which learns from both tasks simultaneously. The promising experimental results show, in particular, the effectiveness of the multitask approach. According to our knowledge, this is the first work that addresses the problem of social media platform identification of videos through the use of shared features.https://www.mdpi.com/2313-433X/7/8/140media forensicssocial media platform identificationvideo forensics |
| spellingShingle | Luca Maiano Irene Amerini Lorenzo Ricciardi Celsi Aris Anagnostopoulos Identification of Social-Media Platform of Videos through the Use of Shared Features Journal of Imaging media forensics social media platform identification video forensics |
| title | Identification of Social-Media Platform of Videos through the Use of Shared Features |
| title_full | Identification of Social-Media Platform of Videos through the Use of Shared Features |
| title_fullStr | Identification of Social-Media Platform of Videos through the Use of Shared Features |
| title_full_unstemmed | Identification of Social-Media Platform of Videos through the Use of Shared Features |
| title_short | Identification of Social-Media Platform of Videos through the Use of Shared Features |
| title_sort | identification of social media platform of videos through the use of shared features |
| topic | media forensics social media platform identification video forensics |
| url | https://www.mdpi.com/2313-433X/7/8/140 |
| work_keys_str_mv | AT lucamaiano identificationofsocialmediaplatformofvideosthroughtheuseofsharedfeatures AT ireneamerini identificationofsocialmediaplatformofvideosthroughtheuseofsharedfeatures AT lorenzoricciardicelsi identificationofsocialmediaplatformofvideosthroughtheuseofsharedfeatures AT arisanagnostopoulos identificationofsocialmediaplatformofvideosthroughtheuseofsharedfeatures |