Uncovering spoken phrases in *encrypted* VoIP conversations
New recent study at *(Johns Hopkins / UNC)* says it can *Uncover spoken phrases in *encrypted* VoIP conversations * *(Johns Hopkins / UNC) ACM paper* We evaluate our techniques on a standard speech recognition corpus containing over 2,000 phonetically rich phrases spoken by 630 distinct speakers from across the continental United States. Our results indicate that we can identify phrases within encrypted calls with an average accuracy of 50%, and with accuracy greater than 90% for some phrases. Clearly, such an attack calls into question the efficacy of current VoIP encryption standards.
More scaremonger tactics from paper authors and journalists... This is for variable bitrate codecs only. Weaknesses in encryption for non-padded VBR codecs have been known for some time. On Tue, Mar 15, 2011 at 2:59 PM, EdPimentl <edpimentl@gmail.com> wrote:
New recent study at (Johns Hopkins / UNC) says it can Uncover spoken phrases in *encrypted* VoIP conversations
(Johns Hopkins / UNC) ACM paper
We evaluate our techniques on a standard speech recognition corpus containing over 2,000 phonetically rich phrases spoken by 630 distinct speakers from across the continental United States. Our results indicate that we can identify phrases within encrypted calls with an average accuracy of 50%, and with accuracy greater than 90% for some phrases. Clearly, such an attack calls into question the efficacy of current VoIP encryption standards.
_______________________________________________ FreeSWITCH-users mailing list FreeSWITCH-users@lists.freeswitch.org http://lists.freeswitch.org/mailman/listinfo/freeswitch-users UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users http://www.freeswitch.org
-- Kristian Kielhofner
On Tue, Mar 15, 2011 at 12:36 PM, Kristian Kielhofner <kris@kriskinc.com>wrote:
More scaremonger tactics from paper authors and journalists...
This is for variable bitrate codecs only. Weaknesses in encryption for non-padded VBR codecs have been known for some time.
Agreed. VBR is, by definition, giving away extra information, and it's been know for a long time to do this. I'd like to see what they got out of non-VBR encrypted streams. Still, I'm gonna check this out to see if there's anything useful underneath the hair-on-fire claims. -MC
participants (3)
-
EdPimentl
-
Kristian Kielhofner
-
Michael Collins