TweepFake: About detecting deepfake tweets.

The recent advances in language modeling significantly improved the generative capabilities of deep neural models: in 2019 OpenAI released GPT-2, a pre-trained language model that can autonomously generate coherent, non-trivial and human-like text samples. Since then, ever more powerful text generat...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Tiziano Fagni, Fabrizio Falchi, Margherita Gambini, Antonio Martella, Maurizio Tesconi
Formato: article
Lenguaje:EN
Publicado: Public Library of Science (PLoS) 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/f931b7470e03463eb28a4bce3caa5e05
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:f931b7470e03463eb28a4bce3caa5e05
record_format dspace
spelling oai:doaj.org-article:f931b7470e03463eb28a4bce3caa5e052021-12-02T20:04:05ZTweepFake: About detecting deepfake tweets.1932-620310.1371/journal.pone.0251415https://doaj.org/article/f931b7470e03463eb28a4bce3caa5e052021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0251415https://doaj.org/toc/1932-6203The recent advances in language modeling significantly improved the generative capabilities of deep neural models: in 2019 OpenAI released GPT-2, a pre-trained language model that can autonomously generate coherent, non-trivial and human-like text samples. Since then, ever more powerful text generative models have been developed. Adversaries can exploit these tremendous generative capabilities to enhance social bots that will have the ability to write plausible deepfake messages, hoping to contaminate public debate. To prevent this, it is crucial to develop deepfake social media messages detection systems. However, to the best of our knowledge no one has ever addressed the detection of machine-generated texts on social networks like Twitter or Facebook. With the aim of helping the research in this detection field, we collected the first dataset of real deepfake tweets, TweepFake. It is real in the sense that each deepfake tweet was actually posted on Twitter. We collected tweets from a total of 23 bots, imitating 17 human accounts. The bots are based on various generation techniques, i.e., Markov Chains, RNN, RNN+Markov, LSTM, GPT-2. We also randomly selected tweets from the humans imitated by the bots to have an overall balanced dataset of 25,572 tweets (half human and half bots generated). The dataset is publicly available on Kaggle. Lastly, we evaluated 13 deepfake text detection methods (based on various state-of-the-art approaches) to both demonstrate the challenges that Tweepfake poses and create a solid baseline of detection techniques. We hope that TweepFake can offer the opportunity to tackle the deepfake detection on social media messages as well.Tiziano FagniFabrizio FalchiMargherita GambiniAntonio MartellaMaurizio TesconiPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 5, p e0251415 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Tiziano Fagni
Fabrizio Falchi
Margherita Gambini
Antonio Martella
Maurizio Tesconi
TweepFake: About detecting deepfake tweets.
description The recent advances in language modeling significantly improved the generative capabilities of deep neural models: in 2019 OpenAI released GPT-2, a pre-trained language model that can autonomously generate coherent, non-trivial and human-like text samples. Since then, ever more powerful text generative models have been developed. Adversaries can exploit these tremendous generative capabilities to enhance social bots that will have the ability to write plausible deepfake messages, hoping to contaminate public debate. To prevent this, it is crucial to develop deepfake social media messages detection systems. However, to the best of our knowledge no one has ever addressed the detection of machine-generated texts on social networks like Twitter or Facebook. With the aim of helping the research in this detection field, we collected the first dataset of real deepfake tweets, TweepFake. It is real in the sense that each deepfake tweet was actually posted on Twitter. We collected tweets from a total of 23 bots, imitating 17 human accounts. The bots are based on various generation techniques, i.e., Markov Chains, RNN, RNN+Markov, LSTM, GPT-2. We also randomly selected tweets from the humans imitated by the bots to have an overall balanced dataset of 25,572 tweets (half human and half bots generated). The dataset is publicly available on Kaggle. Lastly, we evaluated 13 deepfake text detection methods (based on various state-of-the-art approaches) to both demonstrate the challenges that Tweepfake poses and create a solid baseline of detection techniques. We hope that TweepFake can offer the opportunity to tackle the deepfake detection on social media messages as well.
format article
author Tiziano Fagni
Fabrizio Falchi
Margherita Gambini
Antonio Martella
Maurizio Tesconi
author_facet Tiziano Fagni
Fabrizio Falchi
Margherita Gambini
Antonio Martella
Maurizio Tesconi
author_sort Tiziano Fagni
title TweepFake: About detecting deepfake tweets.
title_short TweepFake: About detecting deepfake tweets.
title_full TweepFake: About detecting deepfake tweets.
title_fullStr TweepFake: About detecting deepfake tweets.
title_full_unstemmed TweepFake: About detecting deepfake tweets.
title_sort tweepfake: about detecting deepfake tweets.
publisher Public Library of Science (PLoS)
publishDate 2021
url https://doaj.org/article/f931b7470e03463eb28a4bce3caa5e05
work_keys_str_mv AT tizianofagni tweepfakeaboutdetectingdeepfaketweets
AT fabriziofalchi tweepfakeaboutdetectingdeepfaketweets
AT margheritagambini tweepfakeaboutdetectingdeepfaketweets
AT antoniomartella tweepfakeaboutdetectingdeepfaketweets
AT mauriziotesconi tweepfakeaboutdetectingdeepfaketweets
_version_ 1718375640458067968