Thumbnail Image
Item

When the Few Outweigh the Many: Illicit Content Recognition with Few-Shot Learning

Cascavilla,G.
; 
Catolino,G.
; 
Conti,M.
; 
Mellios,D.
; 
Tamburri,D. A.
Abstract
The anonymity and untraceability benefits of the Dark web account for the exponentially-increased potential of its popularity while creating a suitable womb for many illicit activities, to date. Hence, in collaboration with cybersecurity and law enforcement agencies, research has provided approaches for recognizing and classifying illicit activities with most exploiting textual dark web markets’ content recognition; few such approaches use images that originated from dark web content. This paper investigates this alternative technique for recognizing illegal activities from images. In particular, we investigate label-agnostic learning techniques like One-Shot and Few-Shot learning featuring the use Siamese neural networks, a state-of-the-art approach in the field. Our solution manages to handle small-scale datasets with promising accuracy. In particular, Siamese neural networks reach 90.9% on 20-Shot experiments over a 10-class dataset; this leads us to conclude that such models are a promising and cheaper alternative to the definition of automated law-enforcing machinery over the dark web.
Description
Publisher Copyright: © 2023 by SCITEPRESS - Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0).
Date
2023
Journal Title
Journal ISSN
Volume Title
Publisher
Science and Technology Publications, Lda
Collections
Tilburg University Research Output Collection
Show all metadata
Files
Thumbnail Image
When_the_few_outweigh_the_many.pdf
Adobe PDF, 2.97 MB
Research Projects
Organizational Units
Journal Issue
Keywords
Cybersecurity, Dark Web, Few-Shot Learning, One-Shot Learning, Siamese Neural Network
Citation
Cascavilla, G, Catolino, G, Conti, M, Mellios, D & Tamburri, D A 2023, When the Few Outweigh the Many : Illicit Content Recognition with Few-Shot Learning. in S De Capitani di Vimercati & P Samarati (eds), SECRYPT 2023 - Proceedings of the 20th International Conference on Security and Cryptography. Proceedings of the International Conference on Security and Cryptography, vol. 1, Science and Technology Publications, Lda, pp. 324-334, 20th International Conference on Security and Cryptography, SECRYPT 2023, Rome, Italy, 10/07/23. https://doi.org/10.5220/0012049400003555
URI
https://hdl.handle.net/20.500.14602/25986
License
info:eu-repo/semantics/openAccess
cb
Embedded videos