Naslov
Domain Specific Honeytokens Based on Natural Language Processing - A Conceptual Model

Autori
Turek, Tomislav ; Schatten, Markus ; Kišasondi, Tonimir

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the Central European Conference on Information and Intelligent Systems / Strahonja, Vjeran ; Kirinić, Valentina - Varaždin : Fakultet organizacije i informatike Sveučilišta u Zagrebu, 2018, 207-211

Skup
29th Central European Conference on Information and Intelligent Systems (CECIIS 2018)

Mjesto i datum
Varaždin, Hrvatska, 19.09.2018. - 21.09.2018

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
honeytokens ; honeynets ; information security ; natural language processing ; domain modelling ; keyword generation

Sažetak
This paper presents the idea and conceptual model for keyword modelling by using Natural Language Processing (NLP) in a specific domain. The paper shows that keywords for Honeytokens (HTs) derived from a specific website domain can be generated automatically by extracting concepts of interest from security related or other domain specific texts. A conceptual model for generating such tokens is presented and guidelines for implementation are given. It is argued that such domain specific HTs are a better form of deception technology, that provides a harder challenge for detection from automated attacks and thus improves early detection and incident response procedures in modern complex systems.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti

POVEZANOST RADA