Adversarial attacks on spiking convolutional neural networks for event-based vision

HIGHLIGHTS

• who: Julian Bu00fcchel from the Kerala University of Digital Sciences, India have published the research work: Adversarial attacks on spiking convolutional neural networks for event-based vision, in the Journal: (JOURNAL)
• what: The authors focus on the case of white box attacks, where the attacker has full access to the network and can backpropagate gradients through it. The authors show that these adapted algorithms outperform current state-of-the-art algorithms in the domain of Spiking Convolutional Neural_Network.. The authors show targeted universal attacks on event-based data in the form of adversarial patches, which . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.