Can I read Adversarial Concept Drift Detection Under Poisoning Attacks for Robust Data Stream Mining on EtoBox?

Adversarial Concept Drift Detection Under Poisoning Attacks for Robust Data Stream Mining by Łukasz Korycki; Bartosz Krawczyk is a Computer Science article available to read on EtoBox.

What is Adversarial Concept Drift Detection Under Poisoning Attacks for Robust Data Stream Mining about?

Continuous learning from streaming data is among the most challenging topics in the contemporary machine learning. In this domain, learning algorithms must not only be able to handle massive volume of rapidly arriving data, but also adapt themselves to potential emerging changes. The phenomenon of evolving nature of data streams is known as concept drift. While there is a plethora of methods designed for detecting its occurrence, all of them assume that the drift is connected with underlying changes in the source of data. However, one must consider the possibility of a malicious injection of false data that simulates a concept drift. This adversarial setting assumes a poisoning attack that may be conducted in order to damage the underlying classification system by forcing an adaptation to false data. Existing drift detectors are not capable of differentiating between real and adversarial concept drift. In this paper, we propose a framework for robust concept drift detection in the presence of adversarial and poisoning attacks. We introduce the taxonomy for two types of adversarial concept drifts, as well as a robust trainable drift detector. It is based on the augmented restricted

Who reads Adversarial Concept Drift Detection Under Poisoning Attacks for Robust Data Stream Mining?

Author

Łukasz Korycki; Bartosz Krawczyk

Publisher

Springer Science and Business Media LLC

Published

2022

Language

EN

Field

Computer Science (Physical Sciences)