Perspectives on Adversarial Classification

Adversarial classification (AC) is a major subfield within the increasingly important domain of adversarial machine learning (AML). So far, most approaches to AC have followed a classical game-theoretic framework. This requires unrealistic common knowledge conditions untenable in the security settin...

Descripción completa

Detalles Bibliográficos
Autores: Rios Insua, David, Naveiro, Roi, Gallego, Víctor
Tipo de recurso: artículo
Fecha de publicación:2020
País:España
Institución:Universidad Complutense de Madrid (UCM)
Repositorio:Docta Complutense
Idioma:inglés
OAI Identifier:oai:docta.ucm.es:20.500.14352/7539
Acceso en línea:https://hdl.handle.net/20.500.14352/7539
Access Level:acceso abierto
Palabra clave:004.056
004.492
Classification
adversarial machine learning
security
robustness
adversarial risk analysis
Seguridad informática
Informática (Informática)
Matemáticas (Matemáticas)
1203.17 Informática
12 Matemáticas
Descripción
Sumario:Adversarial classification (AC) is a major subfield within the increasingly important domain of adversarial machine learning (AML). So far, most approaches to AC have followed a classical game-theoretic framework. This requires unrealistic common knowledge conditions untenable in the security settings typical of the AML realm. After reviewing such approaches, we present alternative perspectives on AC based on adversarial risk analysis.