Adversarial Attacks for Drift Detection

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hinder, Fabian, Vaquet, Valerie, Hammer, Barbara
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913680759717888
author Hinder, Fabian
Vaquet, Valerie
Hammer, Barbara
author_facet Hinder, Fabian
Vaquet, Valerie
Hammer, Barbara
contents Concept drift refers to the change of data distributions over time. While drift poses a challenge for learning models, requiring their continual adaption, it is also relevant in system monitoring to detect malfunctions, system failures, and unexpected behavior. In the latter case, the robust and reliable detection of drifts is imperative. This work studies the shortcomings of commonly used drift detection schemes. We show how to construct data streams that are drifting without being detected. We refer to those as drift adversarials. In particular, we compute all possible adversairals for common detection schemes and underpin our theoretical findings with empirical evaluations.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16591
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adversarial Attacks for Drift Detection
Hinder, Fabian
Vaquet, Valerie
Hammer, Barbara
Machine Learning
Concept drift refers to the change of data distributions over time. While drift poses a challenge for learning models, requiring their continual adaption, it is also relevant in system monitoring to detect malfunctions, system failures, and unexpected behavior. In the latter case, the robust and reliable detection of drifts is imperative. This work studies the shortcomings of commonly used drift detection schemes. We show how to construct data streams that are drifting without being detected. We refer to those as drift adversarials. In particular, we compute all possible adversairals for common detection schemes and underpin our theoretical findings with empirical evaluations.
title Adversarial Attacks for Drift Detection
topic Machine Learning
url https://arxiv.org/abs/2411.16591