The Impact on Public Trust of Image Manipulation in Science

López-Cantos, Francisco

doi:10.28945/4407

Cited by 5 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notably, events like the Higgs Boson exploration in 2012 generated a flurry of false information, with as many as 600 tweets per minute [2]. Of particular concern is the use of manipulated images, which can implicitly lend credibility to false narratives, thereby eroding public trust [3,4].…”

Section: Introductionmentioning

confidence: 99%

Detection of Forged Images Using a Combination of Passive Methods Based on Neural Networks

Alencar,

Lopes,

Fernandes

et al. 2024

Future Internet

View full text Add to dashboard Cite

In the current era of social media, the proliferation of images sourced from unreliable origins underscores the pressing need for robust methods to detect forged content, particularly amidst the rapid evolution of image manipulation technologies. Existing literature delineates two primary approaches to image manipulation detection: active and passive. Active techniques intervene preemptively, embedding structures into images to facilitate subsequent authenticity verification, whereas passive methods analyze image content for traces of manipulation. This study presents a novel solution to image manipulation detection by leveraging a multi-stream neural network architecture. Our approach harnesses three convolutional neural networks (CNNs) operating on distinct data streams extracted from the original image. We have developed a solution based on two passive detection methodologies. The system utilizes two separate streams to extract specific data subsets, while a third stream processes the unaltered image. Each net independently processes its respective data stream, capturing diverse facets of the image. The outputs from these nets are then fused through concatenation to ascertain whether the image has undergone manipulation, yielding a comprehensive detection framework surpassing the efficacy of its constituent methods. Our work introduces a unique dataset derived from the fusion of four publicly available datasets, featuring organically manipulated images that closely resemble real-world scenarios. This dataset offers a more authentic representation than other state-of-the-art methods that use algorithmically generated datasets based on image patches. By encompassing genuine manipulation scenarios, our dataset enhances the model’s ability to generalize across varied manipulation techniques, thereby improving its performance in real-world settings. After training, the merged approach obtained an accuracy of 89.59% in the set of validation images, significantly higher than the model trained with only unaltered images, which obtained 78.64%, and the two other models trained using images with a feature selection method applied to enhance inconsistencies that obtained 68.02% for Error-Level Analysis images and 50.70% for the method using Discrete Wavelet Transform. Moreover, our proposed approach exhibits reduced accuracy variance compared to alternative models, underscoring its stability and robustness across diverse datasets. The approach outlined in this work needs to provide information about the specific location or type of tempering, which limits its practical applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Detection of Forged Images Using a Combination of Passive Methods Based on Neural Networks

Alencar,

Lopes,

Fernandes

et al. 2024

Future Internet

View full text Add to dashboard Cite

show abstract

“…Fake news has become a buzzword in the public mind, further eroding the trust in new media and news organizations. Fake news attribution ranges from manipulating images and videos in a scientific context (López-Cantos, 2019) to combat perceptions about news reporting and social media (Cohen, 2019;Gill, 2019). Online news reporting about cyberbullying increases awareness of cyber-safety issues and online dangers for youth in an increasingly complex online world (Zilka, 2017;.…”

Section: Introductionmentioning

confidence: 99%

Trust in Google - A Textual Analysis of News Articles About Cyberbullying

Stegmair

Prybutok

2022

InformingSciJ

View full text Add to dashboard Cite

Aim/Purpose: Cyberbullying (CB) is an ongoing phenomenon that affects youth in negative ways. Using online news articles to provide information to schools can help with the development of comprehensive cyberbullying prevention campaigns, and in restoring faith in news reporting. The inclusion of online news also allows for increased awareness of cybersafety issues for youth. Background: CB is an inherent problem of information delivery and security. Textual analysis provides input into prevention and training efforts to combat the issue. Methodology: Text extraction and text analysis methods of term and concept extraction; text link analysis and sentiment analysis are performed on a body of news articles. Contribution: News articles are determined to be a major source of information for comprehensive cyberbullying prevention campaigns. Findings: Online news articles are relatively neutral in their sentiment; terms and topic extraction provide fertile ground for information presentation and context. Recommendation for Researchers: Researchers should seek support for research projects that extract timely information from online news articles. Future Research: Refinement of the terms and topics analytic model, as well as a system development approach for information extraction of online CB news.

show abstract