Am 07.02.2015 um 04:47 schrieb Reindl Harald:>
> Am 06.02.2015 um 23:13 schrieb SW:
>> According to https://cipherli.st/
>>> ssl = yes
>>> ssl_cert = </etc/dovecot.cert
>>> ssl_key = </etc/dovecot.key
>>> ssl_protocols = !SSLv2 !SSLv3
>>> ssl_cipher_list = AES128+EECDH:AES128+EDH
>>> ssl_prefer_server_ciphers = yes # >Dovecot 2.2.6
>>> Is what you want.
>>
>> Ok, so I have changed my ssl_cipher_list to: ssl_cipher_list >>
AES128+EECDH:AES128+EDH
>>
>> Before I made this change clients were connecting with the following
>> cipher in the log file:
>>
>> ECDHE-ECDSA-AES256-SHA (256/256 bits)
>>
>> After the change the log now says:
>>
>> ECDHE-ECDSA-AES128-GCM-SHA256 (128/128 bits)
>>
>> Is this an improvement (or more secure) despite going from 256bits to
>> 128bits?
>
> yes it is because AES-GCM is currently the best cipher suite while there
> is no point for AES256, if AES128 will fall then it likely affects
> AES256 too and according to Brcue Schneier years ago AES128 has even
> less problems then AES256 (too lazy for google it again)
>
Well, I am working in the crypto field and was a bit astonished about
this "rant" - so a quick search brought up
https://www.schneier.com/blog/archives/2009/07/another_new_aes.html -
for those who want it more compact
http://crypto.stackexchange.com/questions/5118/is-aes-256-weaker-than-192-and-128-bit-versions.
Bottom line: AES256 *IS* better than AES128 for the intended usage but
it is also true that AES-GCM rules out other AES based block ciphers for
other kinds of attacks, so there is no "black or white" answer. To be
honest, I wont worry on this - people who are in the position to break
even a 128bit key will most likely find other ways to get into your mail
communication ;)
Oliver
--
Protect your environment - close windows and adopt a penguin!
-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/pkcs7-signature
Size: 4074 bytes
Desc: S/MIME Cryptographic Signature
URL:
<http://dovecot.org/pipermail/dovecot/attachments/20150207/7c7f3cb8/attachment.p7s>