[Python-Dev] Hash collision security issue (now public)

Thu Dec 29 13:57:07 CET 2011

Hi,
Something I should add to this now that I thought about it a bit more:
Assuming this should be fixed on a language level the solution would
probably be to salt hashes. The most common hash to salt here is the
PyUnicode hash for obvious reasons.
- Option a: Compiled in Salt
 + Easy to implement
 - Breaks unittests most likely (those were broken in the first place
 but that's still a very annoying change to make)
 - Might cause problems with interoperability of Pythons compiled with
 different hash salts
 - You're not really solving the problem because each linux
 distribution (besides Gentoo I guess) would have just one salt
 compiled in and that would be popular enough to have the same
 issue.
- Option b: Environment variable for the salt
 + Easy-ish to implement
 + Easy to synchronize over different machines
 - initialization for base types happens early and unpredictive which
 makes it hard for embedded Python interpreters (think mod_wsgi and
 other things) to specify the salt
- Option c: Random salt at runtime
 + Easy to implement
 - impossible to synchronize
 - breaks unittests in the same way as a compiled in salt would do
Where to add the salt to? Unicode strings and bytestrings (byte
objects) I guess since those are the most common offenders. Sometimes
tuples are keys of dictionaries but in that case a contributing factor
to the hash is the string in the tuple anyways.
Also related: since this is a security related issue, would this be
something that goes into Python 2? Does that affect how a fix would
look like?
Regards,
Armin