Your browser doesn't support javascript.
loading
Robustifying models against adversarial attacks by Langevin dynamics.
Srinivasan, Vignesh; Rohrer, Csaba; Marban, Arturo; Müller, Klaus-Robert; Samek, Wojciech; Nakajima, Shinichi.
Afiliação
  • Srinivasan V; Department of Artificial Intelligence, Fraunhofer Heinrich Hertz Institute, 10587 Berlin, Germany.
  • Rohrer C; Department of Artificial Intelligence, Fraunhofer Heinrich Hertz Institute, 10587 Berlin, Germany.
  • Marban A; Department of Artificial Intelligence, Fraunhofer Heinrich Hertz Institute, 10587 Berlin, Germany; Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany; BIFOLD - Berlin Institute for the Foundations of Learning and Data, Germany.
  • Müller KR; Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany; BIFOLD - Berlin Institute for the Foundations of Learning and Data, Germany; Department of Artificial Intelligence, Korea University, Seoul 136-713, South Korea; Max Planck Institute for Informatics, 66123 Saarbrücken, Ger
  • Samek W; Department of Artificial Intelligence, Fraunhofer Heinrich Hertz Institute, 10587 Berlin, Germany; BIFOLD - Berlin Institute for the Foundations of Learning and Data, Germany. Electronic address: wojciech.samek@hhi.fraunhofer.de.
  • Nakajima S; Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany; BIFOLD - Berlin Institute for the Foundations of Learning and Data, Germany; RIKEN AIP, 1-4-1 Nihonbashi, Chuo-ku, Tokyo 103-0027, Japan. Electronic address: nakajima@tu-berlin.de.
Neural Netw ; 137: 1-17, 2021 May.
Article em En | MEDLINE | ID: mdl-33515855
Assuntos
Palavras-chave
Texto completo
Imprimir
XML
PubMed Links
Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Segurança Computacional / Aprendizado Profundo Tipo de estudo: Prognostic_studies Idioma: En Revista: Neural Netw Assunto da revista: NEUROLOGIA Ano de publicação: 2021 Tipo de documento: Article País de afiliação: Alemanha
Texto completo
Imprimir
XML
PubMed Links
Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Segurança Computacional / Aprendizado Profundo Tipo de estudo: Prognostic_studies Idioma: En Revista: Neural Netw Assunto da revista: NEUROLOGIA Ano de publicação: 2021 Tipo de documento: Article País de afiliação: Alemanha