AI That Listens, Sees, and Understands — On the Edge
always listening

Let’s talk security

12th Aug, 2013
1 min read
Let’s talk security

Here’s another question I hear: If the device is listening for a specific wake up phrase, how do I stop others from using it?

Some users and analysts have noted the amazing sensitivity of Glass. In my own experiments I’ve noticed that it’s even responsive to whispers in a quiet room or speakers from across the room, so it is possible that someone not wearing it can activate it in quiet conditions.

Speaker verification could be added to wake up words, without hurting the power consumption. The settings can be very light to reduce false firing and keep out some percentage of unintended users, or it can be tighter for more security. The “tighter” and higher security means the higher likelihood that the right user won’t always get in, that’s why we use a “light” setting so wrong users are USUALLY kept out and right users virtually always get in. The speaker verification requires training, but this could happen in an “adaptive” fashion with use, so that the training is invisible to the user. The longer the training word or phrase the better the accuracy!

Related Articles

always listening
6th Mar, 2026
The Always-Listening Failure: Why Sensory’s Smart Wakewords are the Future of Voice Interaction
Todd MozerTodd Mozer
3 min read

I have a love/hate relationship with today's premium voice assistants, and the root of the problem is...

Security
18th Feb, 2026
The Smart Home Privacy Gap: Why Cloud Voice Fails Appliances
Todd MozerTodd Mozer
3 min read

Smart home manufacturers face a stark reality: cloud voice AI streams raw audio containing biometric...

Security
6th Feb, 2026
Privacy-by-Design: How On-Device AI Solves GDPR & CCPA
Todd MozerTodd Mozer
3 min read

In the connected device ecosystem, privacy is not optional, it’s a competitive differentiator. As ongoing...