Imagen de Portada
Código QR

Making Machine Learning Robust Against Adversarial Inputs.

The article discusses the failure of machine learning algorithms that exceed human performance in naturally occurring scenarios when an adversary is able to modify their input data. Topics include the use of model training, input validation and architectural changes to defend against adversaries, an...

Descripción completa

Publicado en:Communications of the ACM Vol. 61; no. 7; pp. 56 - 67
Autores principales: GOODFELLOW, IAN, MCDANIEL, PATRICK, PAPERNOT, NICOLAS
Formato: Artículo
Publicado: Association for Computing Machinery Jul2018
Materias:
Machine learning
Algorithms
Computer input design
Computer programming
Computer security
Security systems
Acceso en línea:Ver este registro en EBSCOhost
Sumario:The article discusses the failure of machine learning algorithms that exceed human performance in naturally occurring scenarios when an adversary is able to modify their input data. Topics include the use of model training, input validation and architectural changes to defend against adversaries, and the need for more tools to verify machine learning models in order to prevent attacks by adversaries.