Familiarity-Based Open-Set Recognition Under Adversarial Attacks

Philip  Enevoldsen∗; Christian  Gundersen; Nico Lang; Serge Belongie; Christian Igel

Familiarity-Based Open-Set Recognition Under Adversarial Attacks

Philip Enevoldsen∗, Christian Gundersen, Nico Lang, Serge Belongie, Christian Igel

Research output: Working paper › Preprint

4 Downloads (Pure)

Abstract

Open-set recognition (OSR), the identification of novel categories, can be a critical component when deploying classification models in real-world applications. Recent work has shown that familiarity-based scoring rules such as the Maximum Softmax Probability (MSP) or the Maximum Logit Score (MLS) are strong baselines when the closed-set accuracy is high. However, one of the potential weaknesses of familiarity-based OSR are adversarial attacks. Here, we present gradient-based adversarial attacks on familiarity scores for both types of attacks, False Familiarity and False Novelty attacks, and evaluate their effectiveness in informed and uninformed settings on TinyImageNet.

Original language	English
Publisher	arXiv.org
Number of pages	5
Publication status	Published - 2023

Access to Document

Familiarity-BasedFinal published version, 2.06 MBLicence: CC BY

https://arxiv.org/abs/2311.05006Licence: CC BY

Cite this

@techreport{31dfa6eec5dd491fa88897a41adbcad3,

title = "Familiarity-Based Open-Set Recognition Under Adversarial Attacks",

abstract = "Open-set recognition (OSR), the identification of novel categories, can be a critical component when deploying classification models in real-world applications. Recent work has shown that familiarity-based scoring rules such as the Maximum Softmax Probability (MSP) or the Maximum Logit Score (MLS) are strong baselines when the closed-set accuracy is high. However, one of the potential weaknesses of familiarity-based OSR are adversarial attacks. Here, we present gradient-based adversarial attacks on familiarity scores for both types of attacks, False Familiarity and False Novelty attacks, and evaluate their effectiveness in informed and uninformed settings on TinyImageNet.",

author = "Philip Enevoldsen∗ and Christian Gundersen and Nico Lang and Serge Belongie and Christian Igel",

year = "2023",

language = "English",

publisher = "arXiv.org",

type = "WorkingPaper",

institution = "arXiv.org",

}

TY - UNPB

T1 - Familiarity-Based Open-Set Recognition Under Adversarial Attacks

AU - Enevoldsen∗, Philip

AU - Gundersen, Christian

AU - Lang, Nico

AU - Belongie, Serge

AU - Igel, Christian

PY - 2023

Y1 - 2023

N2 - Open-set recognition (OSR), the identification of novel categories, can be a critical component when deploying classification models in real-world applications. Recent work has shown that familiarity-based scoring rules such as the Maximum Softmax Probability (MSP) or the Maximum Logit Score (MLS) are strong baselines when the closed-set accuracy is high. However, one of the potential weaknesses of familiarity-based OSR are adversarial attacks. Here, we present gradient-based adversarial attacks on familiarity scores for both types of attacks, False Familiarity and False Novelty attacks, and evaluate their effectiveness in informed and uninformed settings on TinyImageNet.

AB - Open-set recognition (OSR), the identification of novel categories, can be a critical component when deploying classification models in real-world applications. Recent work has shown that familiarity-based scoring rules such as the Maximum Softmax Probability (MSP) or the Maximum Logit Score (MLS) are strong baselines when the closed-set accuracy is high. However, one of the potential weaknesses of familiarity-based OSR are adversarial attacks. Here, we present gradient-based adversarial attacks on familiarity scores for both types of attacks, False Familiarity and False Novelty attacks, and evaluate their effectiveness in informed and uninformed settings on TinyImageNet.

M3 - Preprint

BT - Familiarity-Based Open-Set Recognition Under Adversarial Attacks

PB - arXiv.org

ER -