Title:

Attack vectors on supervised machine learning systems in business applications

Group publication title:

Informatyka Ekonomiczna = Business Informatics

Title in english:

Wektory ataków na nadzorowane systemy uczące się w zastosowaniach biznesowych

Creator:

Surma, Jerzy

Subject and Keywords:

adversarial machine learning ; supervised machine learning ; security of machine learning systems ; antagonistyczne maszynowe uczenie się ; nadzorowanie maszynowe uczenie się ; bezpieczeństwo systemów uczących się

Description:

Informatyka Ekonomiczna = Business Informatics, 2020, Nr 3 (57), s. 65-72

Abstrakt:

Machine learning systems have become incredibly popular and now have practical applications in many fields. An area of business applications has been developing particularly well, starting from the prediction of customers’ purchase preferences and up to the automation of critical business processes. In this context, the security of such systems in a situation of a threat of intentional attacks carried by organized crime is extremely important. A theoretical framework of attacks on supervised machine learning systems, which are the most popular in business applications, is set out in this article. The possible attack vectors are widely discussed. The main contribution of this article is to recognize that the black box type attack scenario is the most probable, therefore the scenario of this kind of attacks was described extensively

Publisher:

Wydawnictwo Uniwersytetu Ekonomicznego we Wrocławiu

Place of publication:

Wrocław

Date:

2020

Resource Type:

artykuł

Resource Identifier:

doi:10.15611/ie.2020.3.05

Language:

eng

Relation:

Informatyka Ekonomiczna = Business Informatics, 2020, Nr 3 (57)

Rights:

Pewne prawa zastrzeżone na rzecz Autorów i Wydawcy

Access Rights:

Dla wszystkich zgodnie z licencją

License:

CC BY-SA 4.0

Location:

Uniwersytet Ekonomiczny we Wrocławiu