Illicit Darkweb Classification via Natural-language Processing: Classifying Illicit Content of Webpages based on Textual Information

Giuseppe Cascavilla, Gemma Catolino, Mirella Sangiovanni

2022

Abstract

This work aims at expanding previous works done in the context of illegal activities classification, performing three different steps. First, we created a heterogeneous dataset of 113995 onion sites and dark marketplaces. Then, we compared pre-trained transferable models, i.e., ULMFit (Universal Language Model Fine-tuning), Bert (Bidirectional Encoder Representations from Transformers), and RoBERTa (Robustly optimized BERT approach) with a traditional text classification approach like LSTM (Long short-term memory) neural networks. Finally, we developed two illegal activities classification approaches, one for illicit content on the Dark Web and one for identifying the specific types of drugs. Results show that Bert obtained the best approach, classifying the dark web’s general content and the types of Drugs with 96.08% and 91.98% of accuracy.

Download


Paper Citation


in Harvard Style

Cascavilla G., Catolino G. and Sangiovanni M. (2022). Illicit Darkweb Classification via Natural-language Processing: Classifying Illicit Content of Webpages based on Textual Information. In Proceedings of the 19th International Conference on Security and Cryptography - Volume 1: SECRYPT, ISBN 978-989-758-590-6, pages 620-626. DOI: 10.5220/0011298600003283


in Bibtex Style

@conference{secrypt22,
author={Giuseppe Cascavilla and Gemma Catolino and Mirella Sangiovanni},
title={Illicit Darkweb Classification via Natural-language Processing: Classifying Illicit Content of Webpages based on Textual Information},
booktitle={Proceedings of the 19th International Conference on Security and Cryptography - Volume 1: SECRYPT,},
year={2022},
pages={620-626},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011298600003283},
isbn={978-989-758-590-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Conference on Security and Cryptography - Volume 1: SECRYPT,
TI - Illicit Darkweb Classification via Natural-language Processing: Classifying Illicit Content of Webpages based on Textual Information
SN - 978-989-758-590-6
AU - Cascavilla G.
AU - Catolino G.
AU - Sangiovanni M.
PY - 2022
SP - 620
EP - 626
DO - 10.5220/0011298600003283