BT
Em tela cheia
Fechar tela cheia

Adversarial Attacks on Deep Learning
Gravado em:

| por Eduardo Valle Seguir 0 Seguidores em 30 out 2018 |
  • Mostrar apresentação
  •  
  •  
  •  
36:25

Resumo
In this talk we discuss adversarial attacks formally and informally, and summarize the debate on: are adversarial images a big catastrophic failure? an amusing curiosity? something in-between? We explain how different types of attacks are generated for image classifiers and discuss a why making models resistant to those attacks has proved to difficult.

Minibiografia

Eduardo Valle is a professor at the School of Electrical and Computing Engineering (FEEC) at the State University of Campinas (UNICAMP) since 2010. His research interest include Multimedia Information Retrieval, Content-based Information Retrieval, Large-Scale Machine Learning, Computer Vision. He is particularly interested in applications of Machine Learning for Education and Health.

A segunda edição do PAPIs.io aconteceu em São Paulo nos dias 19, 20 e 21 de Junho de 2018. O evento tem o intuito de apresentar casos reais de utilização de Machine Learning, e contou com mais de 20 palestras, em inglês, apresentando cases e ferramentas de empresas nacionais e internacionais.

BT