skip to main content
Idioma:
Primo Search
Clear Search Box
Search in: Busca Geral
Busca Avançada
Busca por Índices
Tipo de recurso Mostra resultados com: Mostra resultados com: Índice

Vulnerability Estimation of DNN Model Parameters with Few Fault Injections

ZHANG, Yangchao ; ITSUJI, Hiroaki ; UEZONO, Takumi ; TOBA, Tadanobu ; HASHIMOTO, Masanori

IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2023/03/01, Vol.E106.A(3), pp.523-531 [Periódico revisado por pares]

Tokyo: The Institute of Electronics, Information and Communication Engineers

Texto completo disponível

Citações Citado por
  • Título:
    Vulnerability Estimation of DNN Model Parameters with Few Fault Injections
  • Autor: ZHANG, Yangchao ; ITSUJI, Hiroaki ; UEZONO, Takumi ; TOBA, Tadanobu ; HASHIMOTO, Masanori
  • Assuntos: Artificial neural networks ; deep neural network ; fault injection ; malicious attack ; Mathematical models ; Parameter identification ; Radiation effects ; Safety critical ; soft error ; Soft errors ; System failures ; Training ; vulnerability model
  • É parte de: IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2023/03/01, Vol.E106.A(3), pp.523-531
  • Descrição: The reliability of deep neural networks (DNN) against hardware errors is essential as DNNs are increasingly employed in safety-critical applications such as automatic driving. Transient errors in memory, such as radiation-induced soft error, may propagate through the inference computation, resulting in unexpected output, which can adversely trigger catastrophic system failures. As a first step to tackle this problem, this paper proposes constructing a vulnerability model (VM) with a small number of fault injections to identify vulnerable model parameters in DNN. We reduce the number of bit locations for fault injection significantly and develop a flow to incrementally collect the training data, i.e., the fault injection results, for VM accuracy improvement. We enumerate key features (KF) that characterize the vulnerability of the parameters and use KF and the collected training data to construct VM. Experimental results show that VM can estimate vulnerabilities of all DNN model parameters only with 1/3490 computations compared with traditional fault injection-based vulnerability estimation.
  • Editor: Tokyo: The Institute of Electronics, Information and Communication Engineers
  • Idioma: Inglês
Voltar para lista de resultados

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.