Familiarity-Based Open-Set Recognition Under Adversarial Attacks

Autor:	Enevoldsen, Philip, Gundersen, Christian, Lang, Nico, Belongie, Serge, Igel, Christian
Rok vydání:	2023
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: Published in: The 2nd Workshop and Challenges for Out-of-Distribution Generalization in Computer Vision, ICCV 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2311.05006 Zobrazit plný text záznamu View this record from Arxiv