Detecting Cross-Modal Inconsistency to Defend Against Neural Fake News

Reuben Tan, Bryan Plummer, Kate Saenko


Abstract
Large-scale dissemination of disinformation online intended to mislead or deceive the general population is a major societal problem. Rapid progression in image, video, and natural language generative models has only exacerbated this situation and intensified our need for an effective defense mechanism. While existing approaches have been proposed to defend against neural fake news, they are generally constrained to the very limited setting where articles only have text and metadata such as the title and authors. In this paper, we introduce the more realistic and challenging task of defending against machine-generated news that also includes images and captions. To identify the possible weaknesses that adversaries can exploit, we create a NeuralNews dataset which is comprised of 4 different types of generated articles as well as conduct a series of human user study experiments based on this dataset. Coupled with providing a relatively effective approach based on detecting visual-semantic inconsistencies, the valuable insights gleaned from our user study experiments and, consequently, this paper will serve as an effective first line of defense and a valuable reference for future work in defending against machine-generated disinformation.
Anthology ID:
2020.emnlp-main.163
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2081–2106
Language:
URL:
https://aclanthology.org/2020.emnlp-main.163
DOI:
10.18653/v1/2020.emnlp-main.163
Bibkey:
Cite (ACL):
Reuben Tan, Bryan Plummer, and Kate Saenko. 2020. Detecting Cross-Modal Inconsistency to Defend Against Neural Fake News. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2081–2106, Online. Association for Computational Linguistics.
Cite (Informal):
Detecting Cross-Modal Inconsistency to Defend Against Neural Fake News (Tan et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/2020.emnlp-main.163.pdf
Video:
 https://slideslive.com/38938743
Data
NeuralNewsRealNews