Exploiting Multi-domain Visual Information for Fake News Detection

Qi, Peng; Cao, Juan; Yang, Tianyun; Guo, Junbo; Li, Jintao

doi:10.1109/icdm.2019.00062

Cited by 203 publications

(92 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lastly, the work in [62] rely only on visual information but trains in parallel different CNNs operating both in the pixel domain and in the frequency domain. The authors in fact conjecture that frequency-based features can capture different image qualities and compressions potentially due to repeated upload and download from multiple platforms, while pixel-based features can express semantic characteristics of images belonging to fake composite objects.…”

Section: Methods Based On a Reference Datasetmentioning

confidence: 99%

Media forensics on social media platforms: a survey

Pasquini

Amerini

Boato

2021

EURASIP J. on Info. Security

View full text Add to dashboard Cite

The dependability of visual information on the web and the authenticity of digital media appearing virally in social media platforms has been raising unprecedented concerns. As a result, in the last years the multimedia forensics research community pursued the ambition to scale the forensic analysis to real-world web-based open systems. This survey aims at describing the work done so far on the analysis of shared data, covering three main aspects: forensics techniques performing source identification and integrity verification on media uploaded on social networks, platform provenance analysis allowing to identify sharing platforms, and multimedia verification algorithms assessing the credibility of media objects in relation to its associated textual information. The achieved results are highlighted together with current open issues and research challenges to be addressed in order to advance the field in the next future.

show abstract

Section: Methods Based On a Reference Datasetmentioning

confidence: 99%

Media forensics on social media platforms: a survey

Pasquini

Amerini

Boato

2021

EURASIP J. on Info. Security

View full text Add to dashboard Cite

show abstract

“…However, these features are manually crafted and just learn simple patterns, hardly applying to real images. Qi et al (2019) design a CNN-based model to capture image patterns, but their model only works in the case of large samples. So the applicable scope is very limited.…”

Section: Unimodal Fake News Detectionmentioning

confidence: 99%

“…Second, except for texts in tweets, the methods mentioned above all focus on characteristics of images at the semantic level (e.g., emotional provocations), which can be reflected in the spatial domain. However, these methods ignore the individual information of fake images at the physical level, e.g., re-compression artifacts, which is reflected in the frequency domain (Qi et al, 2019). Third, some models (Wang et al, 2018;Khattar et al, 2019) obtain fused representations by simply concatenating multi-modality features.…”

Section: Introductionmentioning

confidence: 99%

Multimodal Fusion with Co-Attention Networks for Fake News Detection

Wu¹,

Zhan²,

Zhang³

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

133

View full text Add to dashboard Cite

Fake news with textual and visual contents has a better story-telling ability than text-only contents, and can be spread quickly with social media. People can be easily deceived by such fake news, and traditional expert identification is labor-intensive. Therefore, automatic detection of multimodal fake news has become a new hot-spot issue. A shortcoming of existing approaches is their inability to fuse multimodality features effectively. They simply concatenate unimodal features without considering inter-modality relations. Inspired by the way people read news with image and text, we propose a novel Multimodal Co-Attention Networks (MCAN) to better fuse textual and visual features for fake news detection. Extensive experiments conducted on two realworld datasets demonstrate that MCAN can learn inter-dependencies among multimodal features and outperforms state-of-the-art methods.

show abstract

“…Unfortunately, this advantage is also taken by fake news which usually contains misrepresented or even tampered images to attract and mislead readers for rapid dissemination. As a result, visual content has become an important part of fake news that can not be neglected [37]. image is an artwork done so beautifully that it is hard to distinguish from reality.…”

Section: Visual Content-basedmentioning

confidence: 99%

“…Misleading images refer to fake news images that have not experienced any manipulation, but as described in a figure the content is misleading. Generally, these misleading photos come from artworks or obsolete pictures that are released at an early event [37].…”

Section: Visual Content-basedmentioning

confidence: 99%

Multimodal fake news detection using a Cultural Algorithm with situational and normative knowledge

Priyanshi

Kobti

2020

2020 IEEE Congress on Evolutionary Computation (CEC)

View full text Add to dashboard Cite

I would like to take this opportunity to express my heartfelt gratitude to all those who not only helped me complete my research thesis but also made my experience at the University of Windsor unforgettable. Firstly, I would like to express my sincere gratitude to my advisor, Dr. Ziad Kobti, for his continued encouragement, inspiration, and tremendous expertise. He gave me the opportunity to choose my study area and discover the Online Social Network domain. His encouragement has supported me in the studies and writing of this thesis. Besides my advisor, I would like to thank my thesis committee, Dr. Mohammed Fazle Baki and Dr. Sherif Saad for their insightful comments and inspiration for the completion of this thesis. I sincerely thank my parents for their love and unconditional care. They have always supported me through these years and motivate me. They have always believed more in me than myself. Also, special thanks to Jainam for always being there and motivating me. I would also like to thank my lab mate Kalyani Selvarajah for helping me with her insights and her skills in writing papers. A special thanks to Shikhar Sanghvi for intriguing ideas and elaborate discussions. Finally, life at Windsor University would not have been what it was without my friends' continued support. I would like to offer my sincere thanks to all my friends who have been vital support throughout my work.

show abstract

Exploiting Multi-domain Visual Information for Fake News Detection

Abstract: The increasing popularity of social media promotes the proliferation of fake news. With the development of multimedia technology, fake news attempts

Cited by 203 publications

References 27 publications

Media forensics on social media platforms: a survey

Media forensics on social media platforms: a survey

Multimodal Fusion with Co-Attention Networks for Fake News Detection

Multimodal fake news detection using a Cultural Algorithm with situational and normative knowledge

Contact Info

Product

Resources

About