There was a recent story about the voice control on the Xbox One that is a good reminder about potential problems with this security paradigm. The latest commercial has an actor bringing up his box with the "Xbox on" command. The problem is that apparently Xbox Ones were turning themselves on when hearing the commercial. A video of a user saying the password might just do the same here. One possibility might be to have the tablet ask a simple question as a secondary check. That would make a recorded crack harder.
I think most users will find the convenience vs. security trade-off a worthwhile one. True, a combination of facial recognition plus voice recognition is not completely secure, but neither is the 4-digit PIN if someone looks over your shoulder while you enter it. The number of times per day the average smartphone user needs to do this is enough to become annoying, so a faster method that has "good enough" security will be a welcome improvement.
One interesting concept of security and especially for crypto systems is Shamir's Law which states that security / cryptography is not broken / cracked but bypassed and there are many examples of this holding true.
This is pretty amazing -- they gave me Skype-based demo when I was being briefed -- much like the YouTube video above -- it's amazing to see someone tap on an application like Facebook and the application "looks at you" and recognizes you and grants you immediate access.
And the higher security stuff that also requires voice identification -- and that works even in noisy environments -- is really rather clever.
What are the engineering and design challenges in creating successful IoT devices? These devices are usually small, resource-constrained electronics designed to sense, collect, send, and/or interpret data. Some of the devices need to be smart enough to act upon data in real time, 24/7. Specifically the guests will discuss sensors, security, and lessons from IoT deployments.