Faster Repeated Evasion Attacks in Tree Ensembles

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00381743" target="_blank" >RIV/68407700:21230/24:00381743 - isvavai.cz</a>

Výsledek na webu

<a href="https://papers.nips.cc/paper_files/paper/2024/file/2c23b3c72127e15fedc276722faee927-Paper-Conference.pdf" target="_blank" >https://papers.nips.cc/paper_files/paper/2024/file/2c23b3c72127e15fedc276722faee927-Paper-Conference.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Faster Repeated Evasion Attacks in Tree Ensembles

Popis výsledku v původním jazyce

Tree ensembles are one of the most widely used model classes. However, these mod- els are susceptible to adversarial examples, i.e., slightly perturbed examples that elicit a misprediction. There has been significant research on designing approaches to construct such examples for tree ensembles. But this is a computationally chal- lenging problem that often must be solved a large number of times (e.g., for all examples in a training set). This is compounded by the fact that current approaches attempt to find such examples from scratch. In contrast, we exploit the fact that multiple similar problems are being solved. Specifically, our approach exploits the insight that adversarial examples for tree ensembles tend to perturb a consistent but relatively small set of features. We show that we can quickly identify this set of features and use this knowledge to speedup constructing adversarial examples.

Název v anglickém jazyce

Faster Repeated Evasion Attacks in Tree Ensembles

Popis výsledku anglicky

Tree ensembles are one of the most widely used model classes. However, these mod- els are susceptible to adversarial examples, i.e., slightly perturbed examples that elicit a misprediction. There has been significant research on designing approaches to construct such examples for tree ensembles. But this is a computationally chal- lenging problem that often must be solved a large number of times (e.g., for all examples in a training set). This is compounded by the fact that current approaches attempt to find such examples from scratch. In contrast, we exploit the fact that multiple similar problems are being solved. Specifically, our approach exploits the insight that adversarial examples for tree ensembles tend to perturb a consistent but relatively small set of features. We show that we can quickly identify this set of features and use this knowledge to speedup constructing 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

—

Návaznosti

R - Projekt Ramcoveho programu EK

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the NeurIPS

ISBN

979-8-3313-1438-5

ISSN

1049-5258

e-ISSN

—

Počet stran výsledku

33

Strana od-do

—

Název nakladatele

Neural Information Processing Systems (NIPS) Foundation

Místo vydání

—

Místo konání akce

Vancouver

Datum konání akce

10. 12. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—