Skip to main content

Table 4 Average collisions per gene sequence word varying base word size for 32 and 64-bit hash codes

From: Polymorphic malware detection using sequence classification methods and ensembles

Hash size

Sequence

Avg. seq. words per hash value

32 bits

31 base word

1 073 741 824

64 bits

31 base word

0.25

32 bits

16 base word

1

64 bits

32 base word

1