Effect of text augmentation and adversarial training on fake news detection

Par Conseil national de recherches du Canada

Téléchargement	Voir le manuscrit accepté : Effect of text augmentation and adversarial training on fake news detection (PDF, 1.5 Mio)
DOI	Trouver le DOI : https://doi.org/10.1109/TCSS.2023.3344597
Auteur	Rechercher : Ahmed, Hadeer Identifiant ORCID : https://orcid.org/0000-0001-9568-1563; Rechercher : Traore, Issa Identifiant ORCID : https://orcid.org/0000-0003-2987-8047; Rechercher : Saad, Sherif Identifiant ORCID : https://orcid.org/0000-0002-5506-5261; Rechercher : Mamun, Mohammad¹Identifiant ORCID : https://orcid.org/0000-0002-4045-8687
Affiliation	Conseil national de recherches du Canada. Technologies numériques
Format	Texte, Article
Sujet	meaning representation (AMR); adversarial training; clonal selection algorithm; cyberattack; fake news; graph representation; text generation; data models; training; machine learning; training data; data augmentation; social networking (online)
Résumé	The action of spreading false information through fake news articles presents a significant danger to society because it has the ability to shape public opinion with inaccurate facts. This can lead to negative effects, such as reduced trust in institutions and the promotion of conflict, division, and even violence. In this article, a text augmentation technique is introduced as a means of generating new data from preexisting fake news datasets. This approach has the potential to enhance classifier performance by a range of 3%–11%. It can also be utilized to launch a successful attack on trained classifiers, with up to a 90% success rate. However, the success rate of these attacks decreased to less than 28% when the model was retrained with the generated adversarial examples. These results demonstrate the effectiveness of text augmentation as a viable method for detecting fake news and increasing classifier accuracy and performance, as well as its ability to be utilized to perform adversarial machine learning (ML) and improve the resilience of ML algorithms.
Date de publication	2024-01-12
Maison d’édition	Institute of Electrical and Electronics Engineers
Dans	IEEE Transactions on Computational Social Systems (12 janvier 2024).
Langue	anglais
Sous presse	Oui
Publications évaluées par des pairs	Oui
Exporter la notice	Exporter en format RIS
Signaler une correction	Signaler une correction (s'ouvre dans un nouvel onglet)
Identificateur de l’enregistrement	34458b13-f5d9-4c67-8549-781b36951a8d
Enregistrement créé	2024-04-03
Enregistrement modifié	2024-05-16

Date de modification :: 2024-07-18