Neurosca: evolving activation functions for side-channel analysis

HIGHLIGHTS

• who: KARLO KNEu017dEVIu0106 and colleagues from the of Electrical Engineering, University of Zagreb, Zagreb, Croatia Systems, Delft University of Technology, CD Delft, The Netherlands have published the research work: NeuroSCA: Evolving Activation Functions for Side-Channel Analysis, in the Journal: (JOURNAL)
• what: The authors demonstrate that evolutionary algorithms can evolve new activation functions for side-channel analysis (SCA) outperforming ReLU other activation functions commonly applied to that problem. The analysis shows that certain nodes have more influence when constructing new activation functions, and as such, should be favored during the evolution process. The authors evaluate . . .
  

   

  

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

  Thanks :)

  Username or E-mail:

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