When Should You Defend Your Classifier? A Game-Theoretical Analysis of Countermeasures Against Adversarial Examples

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00356237" target="_blank" >RIV/68407700:21230/21:00356237 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-030-90370-1_9" target="_blank" >https://doi.org/10.1007/978-3-030-90370-1_9</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-90370-1_9" target="_blank" >10.1007/978-3-030-90370-1_9</a>

Jazyk výsledku

angličtina

Název v původním jazyce

When Should You Defend Your Classifier? A Game-Theoretical Analysis of Countermeasures Against Adversarial Examples

Popis výsledku v původním jazyce

Adversarial machine learning, i.e., increasing the robustness of machine learning algorithms against so-called adversarial examples, is now an established field. Yet, newly proposed methods are evaluated and compared under unrealistic scenarios where costs for adversary and defender are not considered and either all samples or no samples are adversarially perturbed. We scrutinize these assumptions and propose the advanced adversarial classification game, which incorporates all relevant parameters of an adversary and a defender. Especially, we take into account economic factors on both sides and the fact that all so far proposed countermeasures against adversarial examples reduce accuracy on benign samples. Analyzing the scenario in detail, where both players have two pure strategies, we identify all best responses and conclude that in practical settings, the most influential factor might be the maximum amount of adversarial examples.

Název v anglickém jazyce

When Should You Defend Your Classifier? A Game-Theoretical Analysis of Countermeasures Against Adversarial Examples

Popis výsledku anglicky

Adversarial machine learning, i.e., increasing the robustness of machine learning algorithms against so-called adversarial examples, is now an established field. Yet, newly proposed methods are evaluated and compared under unrealistic scenarios where costs for adversary and defender are not considered and either all samples or no samples are adversarially perturbed. We scrutinize these assumptions and propose the advanced adversarial classification game, which incorporates all relevant parameters of an adversary and a defender. Especially, we take into account economic factors on both sides and the fact that all so far proposed countermeasures against adversarial examples reduce accuracy on benign samples. Analyzing the scenario in detail, where both players have two pure strategies, we identify all best responses and conclude that in practical settings, the most influential factor might be the maximum amount of adversarial examples.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

International Conference on Decision and Game Theory for Security

ISBN

978-3-030-90369-5

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

20

Strana od-do

158-177

Název nakladatele

Springer Nature Switzerland AG

Místo vydání

Basel

Místo konání akce

Online conference

Datum konání akce

25. 10. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—