Your post is very informative. Smartphone security is very necessary for all. Many users put some important data on it. Now many electronic companies provide anti theft systems for smart phones. Shopguard Canada is a popular company for this service.
@DrQuine: It seems to me that the changes in faces associated with lighting, changed facial hair (shaving beards), injuries, and aging make the face a moving target.
The one thing about the folks at Sensory is that they are extremely good at what they do -- I hope to visit their labs one day and really sit down with their techno-weenies and ask about stuff like this.
It seems to me that the changes in faces associated with lighting, changed facial hair (shaving beards), injuries, and aging make the face a moving target. For the algorithm to be flexible enough to tolerate those changes suggests that a mask or video image might also pass. Likewise, our voices change with stress, illness (that heavy voice that comes with a cold), and perhaps even mood. I'd guess a good recording would be more reliable than the live person. Face and voice recognition strike me as less reliable than a fingerprint reader (which could be placed on the blank back of the smartphone to save real estate).
@betajet: Well, it wouldn't be very secure in my case. My mother says "all bearded men look alike"...
I've seen your beard -- very impressive -- I'd recognise it anywhere LOL
I posted your point to the folks at Sensory, and they replied as follows:
The more hidden the face the less accurate the vision will be, however this is a big reason why we use dual biometrics. A similarity in face—as for example, 10 heavily bearded men, would not affect the voice component--the voice verification component will still prevent a similar looking person from getting in. This is a big reason why we use the dual biometrics of combined voice and vision.
@goafrit: Hope it can decipher when there is threat and the voice changes. People seem to speak differently under threat than in normal times.
Good point -- I guess it deprends what the threat is:
a) If someone is pointing a gun at your head telling you to say your secret phrase, then you may (or may not) be relieved when your tablet computer refuses to accept your voice signature.
b) If you've just discovered a bomb and you wish to alert the authorities, you'd probably be a tad disgruntled if your smartphone decided it wasn't you talking.
Having said all this:
i) The changes that someone will be holding a gut to your head to gain access to the games on your iPad are slight.
ii) You will probably be able to make emergency calls without logging on.
iii) I'm sure you can always fall back on entering a PIN or password.
iv) These are still the early days -- in the future the device may have multiple cameras and it may be able to work out that you are under stress and why you are under stress and take appropriate action (like calling the authorities on your behalf)
>> The idea of having the security verification on the device, rather than in the cloud, has a lot of appeal.
That is the most important improvement in security in the last 5 years. The premise is that unless you have control of the hardware, you cannot get access. No one has respected the patent because it was a bad guy Kim DotCOM that filed it many years ago. Everyone is violating it. That happens when a hacker files a patent on how to protect from hacking.
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. Are the design challenges the same as with embedded systems, but with a little developer- and IT-skills added in? What do engineers need to know? Rick Merritt talks with two experts about the tools and best options for designing IoT devices in 2016. Specifically the guests will discuss sensors, security, and lessons from IoT deployments.