Social Media Origin Based Image Tracing Using Deep CNN

Siddiqui, Nadia; Anjum, Areesha; Saleem, Mahreen; Islam, Saiful

doi:10.1109/iciip47207.2019.8985933

Cited by 10 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bharati et al [4] proposed a method that utilizes non-content-based information to extract the path of a particular image that has gone through the Internet without the sizeable computational overhead. Siddiqui et al [19] introduced a model to find these distinct traces by utilizing Deep Learning based approaches to look at the image's social network of origin, focusing on determining which social network the particular image was downloaded from.…”

Section: Related Workmentioning

confidence: 99%

Practical Analyses of How Common Social Media Platforms and Photo Storage Services Handle Uploaded Images

Dang-Nguyen¹,

Sjøen²,

Le³

et al. 2023

Preprint

View full text Add to dashboard Cite

The research done in this study has delved deeply into the changes made to digital images that are uploaded to three of the major social media platforms and image storage services in today's society: Facebook, Flickr, and Google Photos. In addition to providing up-to-date data on an ever-changing landscape of different social media networks' digital fingerprints, a deep analysis of the social networks' filename conventions has resulted in two new approaches in (i) estimating the true upload date of Flickr photos, regardless of whether the dates have been changed by the user or not, and regardless of whether the image is available to the public or has been deleted from the platform; (ii) revealing the photo ID of a photo uploaded to Facebook based solely on the file name of the photo.

show abstract

Section: Related Workmentioning

confidence: 99%

Practical Analyses of How Common Social Media Platforms and Photo Storage Services Handle Uploaded Images

Dang-Nguyen¹,

Sjøen²,

Le³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Political party PTI used the slogan "Change has come" (Tabdeli agai hai) to win votes after years of fighting for political power. The people also liked the PTI's stand on "one education system" (Siddiqui, Anjum, Saleem, & Islam, 2019).…”

Section: And 2018 Elections; a Psychological Evolution Of Emotional A...mentioning

confidence: 99%

Revisiting the Dynamics of Political Persuasion and the Psychology of Emotional Appeals in Pakistani Political Campaigns

Noor,

Pasha,

Siddiqui

2022

pjsr

View full text Add to dashboard Cite

Politico-psychological studies have revealed, Political campaigns have traditionally used for emotional appeals to engage with people. This study examines the efficacy, influence, and ethics of emotional appeals in Pakistani political campaigns. Through case studies and a literature analysis, this research examines politicians' emotional appeals, their effects on voters, and their ethical implications. The study included primary and secondary sources. The data shows that Pakistani political campaigns get benefit from emotional appeals. These appeals had symbolic, psychological, and collocative effects. These chants are also utilized in Pakistan to boost self-esteem and denigrate others. These outcomes raise concerns about manipulation and exploitation. The article concludes that ethical considerations and fair and balanced use of emotional appeals in political campaigns are crucial. Keyword: Psychological appeals, Emotions, Political Persuasion, Voter behavior.

show abstract

“…Moreover, the human ability to learn from experience and reuse what has been learned in new contexts is still difficult to reproduce in machine learning as well as in multimedia forensics. All these reasons, along with the unavailability of large training datasets containing both video and image content, have led researchers to treat the problems of social-media-platform identification of images [4][5][6][7] and videos [8] separately. Recently, Iuliani et al [9] showed that it is possible to identify the source of a digital video by exploiting a reference sensor pattern noise generated by still images taken by the same device, suggesting that images and videos share some forensic traces.…”

Section: Introductionmentioning

confidence: 99%

Identification of Social-Media Platform of Videos through the Use of Shared Features

Maiano

Amerini

Celsi³

et al. 2021

J. Imaging

View full text Add to dashboard Cite

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.

show abstract

Social Media Origin Based Image Tracing Using Deep CNN

Cited by 10 publications

References 16 publications

Practical Analyses of How Common Social Media Platforms and Photo Storage Services Handle Uploaded Images

Practical Analyses of How Common Social Media Platforms and Photo Storage Services Handle Uploaded Images

Revisiting the Dynamics of Political Persuasion and the Psychology of Emotional Appeals in Pakistani Political Campaigns

Identification of Social-Media Platform of Videos through the Use of Shared Features

Contact Info

Product

Resources

About