Skip to main content

Table 7 Speedup in popular first-order masking schemes on an Intel Core i7-4790 CPU with “-O3” compiler option running at 3.60GHz

From: A secure and highly efficient first-order masking scheme for AES linear operations

Scheme Linear Operations First-Order Security GF256MUL2 1 Time [us] Speedup2
Unprotected AES Original Implementation No Computation 3.178
    LUT 0.362  
  Improved Implementation No Computation 0.400  
    LUT 0.362  
SP Original Implementation No Computation 0.587
    LUT 0.523  
  Improved Implementation No Computation 0.562  
    LUT 0.533  
  Our Proposal Yes Computation 0.528  
    LUT 0.599  
ASCAD Original Implementation Yes Computation 0.847
    LUT 0.734  
  Improved Implementation Yes Computation 0.793  
    LUT 0.732  
  Our Proposal Yes Computation 0.775 2.32%
    LUT 0.693 5.63%
RSMv1 Original Implementation No Computation 0.775
    LUT 0.666  
  Improved Implementation No Computation 0.734  
    LUT 0.660  
  Our Proposal Yes Computation 0.665  
    LUT 0.593  
RSMv2 Original Implementation Yes Computation 0.969
    LUT 0.840  
  Improved Implementation Yes Computation 0.909  
    LUT 0.845  
  Our Proposal Yes Computation 0.893 1.79%
    LUT 0.819 3.17%
  More Efficient Proposal Yes Computation 0.809 12.36%
    LUT 0.795 6.29%