Interpretable Biometrics: Should We Rethink How Presentation Attack Detection is Evaluated?

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2020

Autores

Ana F. Sequeira (Autor) Outra; Wilson Silva (Autor) Outra; João Ribeiro Pinto (Autor) Outra; Tiago Gonçalves (Autor) Outra; Jaime S. Cardoso (Autor) FEUP

Ata de Conferência Internacional

Título: 8th International Workshop on Biometrics and Forensics, IWBF 2020, Porto, Portugal, April 29-30, 2020

Páginas: 1-6

8th International Workshop on Biometrics and Forensics, IWBF 2020

29 April 2020 through 30 April 2020

Indexação

ISI Web of Knowledge - 6 Citações

Scopus - 9 Citações

Outras Informações

ID Authenticus: P-00S-C9S

DOI: 10.1109/iwbf49977.2020.9107949

Abstract (EN): Presentation attack detection (PAD) methods are commonly evaluated using metrics based on the predicted labels. This is a limitation, especially for more elusive methods based on deep learning which can freely learn the most suitable features. Though often being more accurate, these models operate as complex black boxes which makes the inner processes that sustain their predictions still baffling. Interpretability tools are now being used to delve deeper into the operation of machine learning methods, especially artificial networks, to better understand how they reach their decisions. In this paper, we make a case for the integration of interpretability tools in the evaluation of PAD. A simple model for face PAD, based on convolutional neural networks, was implemented and evaluated using both traditional metrics (APCER, BPCER and EER) and interpretability tools (Grad-CAM), using data from the ROSE Youtu video collection. The results show that interpretability tools can capture more completely the intricate behavior of the implemented model, and enable the identification of certain properties that should be verified by a PAD method that is robust, coherent, meaningful, and can adequately generalize to unseen data and attacks. One can conclude that, with further efforts devoted towards higher objectivity in interpretability, this can be the key to obtain deeper and more thorough PAD performance evaluation setups. © 2020 IEEE.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 6