Re:De-anonymizing programmers from executable binaries
by haberman on Friday March 16, 2018 @01:36PM
(#16602369)
I would be very interested to know how the accuracy changes if you remove symbols and strings from the analysis.
Symbols and strings are free-form text that would seem to leave a lot more of a stylistic fingerprint. If you could get this level of accuracy from machine code alone, I would be very surprised.
The article says that stripping symbols reduced accuracy by 24%. This is a far greater drop than from optimizing the binary. It leads me to believe that a large part of the success in classifying is coming from symbols and strings.
Symbols and strings are free-form text that would seem to leave a lot more of a stylistic fingerprint. If you could get this level of accuracy from machine code alone, I would be very surprised.
The article says that stripping symbols reduced accuracy by 24%. This is a far greater drop than from optimizing the binary. It leads me to believe that a large part of the success in classifying is coming from symbols and strings.