Please use this identifier to cite or link to this item:
http://hdl.handle.net/2122/15150
Authors: | Campanile, Lelio* Cantiello, Pasquale* Iacono, Mauro* Marulli, Fiammetta* Mastroianni, Michele* |
Title: | Vulnerabilities Assessment of Deep Learning-Based Fake News Checker Under Poisoning Attacks | Publisher: | Springer Nature Switzerland | Issue Date: | 2021 | ISBN: | 978-3-030-91433-2 | Keywords: | Natural Language Processing Fake news Adversarial attacks Data poisoning attacks Deep neural network resilience |
Subject Classification: | 05.09. Miscellaneous | Abstract: | In this work, we envise an effective case study concerning a data and a model poisoning attack, consisting in evaluating how much a poisoned word embeddings model could affect the reliability of a deep neural network-based Fake News Checker; furthermore, we plan to train three different word embeddings models among the most performing in the Natural Language Processing field, in order to investigate which of these models can be considered more resilient and robust when such kind of attacks are applied. |
Appears in Collections: | Book chapters |
Files in This Item:
File | Description | Size | Format | Existing users please Login |
---|---|---|---|---|
CSoNet2021.pdf | Restricted chapter | 2.69 MB | Adobe PDF | |
CSoNet_submitted.pdf | submitted | 115.67 kB | Adobe PDF | View/Open |
Page view(s)
32
checked on Mar 27, 2024
Download(s)
50
checked on Mar 27, 2024