Designing an attack-defense game: how to increase robustness of financial transaction models via a competition

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zaytsev, Alexey, Kovaleva, Maria, Natekin, Alex, Vorsin, Evgeni, Smirnov, Valerii, Smirnov, Georgii, Sidorshin, Oleg, Senin, Alexander, Dudin, Alexander, Berestnev, Dmitry
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910611509608448
author Zaytsev, Alexey
Kovaleva, Maria
Natekin, Alex
Vorsin, Evgeni
Smirnov, Valerii
Smirnov, Georgii
Sidorshin, Oleg
Senin, Alexander
Dudin, Alexander
Berestnev, Dmitry
author_facet Zaytsev, Alexey
Kovaleva, Maria
Natekin, Alex
Vorsin, Evgeni
Smirnov, Valerii
Smirnov, Georgii
Sidorshin, Oleg
Senin, Alexander
Dudin, Alexander
Berestnev, Dmitry
contents Banks routinely use neural networks to make decisions. While these models offer higher accuracy, they are susceptible to adversarial attacks, a risk often overlooked in the context of event sequences, particularly sequences of financial transactions, as most works consider computer vision and NLP modalities. We propose a thorough approach to studying these risks: a novel type of competition that allows a realistic and detailed investigation of problems in financial transaction data. The participants directly oppose each other, proposing attacks and defenses -- so they are examined in close-to-real-life conditions. The paper outlines our unique competition structure with direct opposition of participants, presents results for several different top submissions, and analyzes the competition results. We also introduce a new open dataset featuring financial transactions with credit default labels, enhancing the scope for practical research and development.
format Preprint
id arxiv_https___arxiv_org_abs_2308_11406
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Designing an attack-defense game: how to increase robustness of financial transaction models via a competition
Zaytsev, Alexey
Kovaleva, Maria
Natekin, Alex
Vorsin, Evgeni
Smirnov, Valerii
Smirnov, Georgii
Sidorshin, Oleg
Senin, Alexander
Dudin, Alexander
Berestnev, Dmitry
Machine Learning
Cryptography and Security
Statistical Finance
Banks routinely use neural networks to make decisions. While these models offer higher accuracy, they are susceptible to adversarial attacks, a risk often overlooked in the context of event sequences, particularly sequences of financial transactions, as most works consider computer vision and NLP modalities. We propose a thorough approach to studying these risks: a novel type of competition that allows a realistic and detailed investigation of problems in financial transaction data. The participants directly oppose each other, proposing attacks and defenses -- so they are examined in close-to-real-life conditions. The paper outlines our unique competition structure with direct opposition of participants, presents results for several different top submissions, and analyzes the competition results. We also introduce a new open dataset featuring financial transactions with credit default labels, enhancing the scope for practical research and development.
title Designing an attack-defense game: how to increase robustness of financial transaction models via a competition
topic Machine Learning
Cryptography and Security
Statistical Finance
url https://arxiv.org/abs/2308.11406