Current solutions to tackle phishing employ blocklists that are built from user reports or automatic approaches. They, however, fall short in detecting zero-day phishing attacks. We propose the use of Generative Adversarial Networks (GANs) to automate the generation of new squatting candidates starting from a list of benign URLs. The candidates can be either manually verified or become part of a training set for existing machine learning models. Our results show that GANs can produce squatting candidates, some of which are previously unknown existing phishing domains.
Augmenting phishing squatting detection with GANs
Trevisan, Martino;
2021-01-01
Abstract
Current solutions to tackle phishing employ blocklists that are built from user reports or automatic approaches. They, however, fall short in detecting zero-day phishing attacks. We propose the use of Generative Adversarial Networks (GANs) to automate the generation of new squatting candidates starting from a list of benign URLs. The candidates can be either manually verified or become part of a training set for existing machine learning models. Our results show that GANs can produce squatting candidates, some of which are previously unknown existing phishing domains.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
3488658.3493787.pdf
Accesso chiuso
Licenza:
Non specificato
Dimensione
1.24 MB
Formato
Adobe PDF
|
1.24 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
3488658.3493787-Post_print.pdf
accesso aperto
Tipologia:
Bozza finale post-referaggio (post-print)
Licenza:
Digital Rights Management non definito
Dimensione
1.81 MB
Formato
Adobe PDF
|
1.81 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.