It has been shown that many Authorship Identification systems are vulnerable to adversarial attacks, where an author actively tries to fool the classifier. We propose to tackle the adversarial Authorship Verification task by augmenting the training set with synthetic textual examples. In this ongoing study, we present preliminary results using two learning algorithms (SVM and Neural Network), and two generation strategies (based on language modeling and GAN training) for two generator models, on three datasets. We empirically show that data augmentation may help improve the performance of the classifier in an adversarial setup.
Enhancing adversarial authorship verification with data augmentation
Corbara S;
2023
Abstract
It has been shown that many Authorship Identification systems are vulnerable to adversarial attacks, where an author actively tries to fool the classifier. We propose to tackle the adversarial Authorship Verification task by augmenting the training set with synthetic textual examples. In this ongoing study, we present preliminary results using two learning algorithms (SVM and Neural Network), and two generation strategies (based on language modeling and GAN training) for two generator models, on three datasets. We empirically show that data augmentation may help improve the performance of the classifier in an adversarial setup.File | Dimensione | Formato | |
---|---|---|---|
prod_486039-doc_201546.pdf
accesso aperto
Descrizione: Enhancing adversarial authorship verification with data augmentation
Tipologia:
Versione Editoriale (PDF)
Dimensione
258.83 kB
Formato
Adobe PDF
|
258.83 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.