phc-discussions - Re: [PHC] A review per day

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <540715F1.4040709@ciphershed.org>
Date: Wed, 03 Sep 2014 09:21:53 -0400
From: Bill Cox <waywardgeek@...hershed.org>
To: discussions@...sword-hashing.net
Subject: Re: [PHC] A review per day - Parallel

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

I am going to personally give Parallel a qualified "A" grade, and
suggest to the judges that Parallel make it to the next round.

Do we have any graphics experts here who could chime in?

The competition has no other entry designed to make use of graphics
accelerators for defensive purposes.  Even our cell phones have
graphics hardware now days.  It seems crazy not to use these resources
for defensive purposes.  I would hate to see our only entry in this
category get dropped from the competition.

My only qualification is that I think SHA512 is a poor choice for hash
function, as is SHA256, Blake2b, SHA3, and every other cryptographic
hash.  Every one of these is designed for cheap and fast
implementation in an ASIC!

What I would like to see for Parallel is an effort to find a graphics
accelerator optimized hashing function which is hard to implement in
an ASIC.  I do not feel it needs to be a cryptographically strong
hashing function, just something that doesn't lose entropy and which
the attacker can't compute with short-cuts.  It should be difficult to
accelerate in an ASIC, so it probably needs to make parallel use of
the cores and memory commonly available on graphics accelerators.

Surely graphics experts could help us here.  I bet there are some
pretty awesome graphics-acceleration-hard solutions waiting to be
found that will simply trash ASIC attacks.

Without a graphics-card optimized hashing function option, I would
have trouble recommending that Parallel deserves to be one of the PHC
winners.  With such a function, I hope it will be.

I am willing to help with the ASIC defense analysis.  If there were a
graphics expert here I could work with, we might be able to help Steve
out.

Bill
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
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=dvmo
-----END PGP SIGNATURE-----