Stories
Slash Boxes
Comments

SoylentNews is people

posted by Fnord666 on Saturday March 14 2020, @03:40PM   Printer-friendly
from the what-was-that-you-said? dept.

Arthur T Knackerbracket has found the following story:

So how often are smart speakers listening when they shouldn't? A team of researchers at Boston's Northeastern University are conducting an ongoing study to determine just how bad the problem really is. They've set up an experiment to generate unexpected activation triggers and study them inside and out.

The team corralled a group of mainstream smart speakers into a box representing all the major players — four Alexas and one each of her cohorts. We'd love to see them maximize the test subjects by including enough devices of each type to cover all the possible assigned wake words, but that would be pretty expensive.

Then they piped in 125 hours worth of audio from TV shows with rapid-fire dialogue using Netflix. The shows they chose are healthy cross-section of televised entertainment — mostly newer stuff, but some going back a decade or more. Everything from comedy to drama. A video camera trained on the speakers will record any lights that indicate a successful activation. There's also a microphone to pick up anything the devices say in response to the dialogue stream, and a WAP to capture network traffic in and out of the box.

While the results indicate that these devices aren't constantly recording (phew!), they do tend to wake up quite frequently for short periods of time — up to 19 times in a 24-hour period. The worst offenders were the Apple and Microsoft speakers, both of which activated more often than the others. Not all of the activations were short and sweet, though — both the Microsoft Invoke and the Echo Dot had accidental activations lasting up to 43 seconds long. That's plenty of time to record and/or distribute your late-night 16-digit utterances to the QVC operators, or the secret ingredient in your mother-in-law's Quiche Lorraine.

-- submitted from IRC


Original Submission

 
This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
  • (Score: 1, Interesting) by Anonymous Coward on Sunday March 15 2020, @03:22AM

    by Anonymous Coward on Sunday March 15 2020, @03:22AM (#971463)

    recording (phew!)"

    I think you need to qualify that. They are certainly always listening. If they weren't they wouldn't be able to tell if you asked them a question. So the concept of "recording" here needs to be considered. Probably they aren't doing this in an ASIC, so yes they probably are always recording. They are just usually recording to a cache. They just aren't dumping the cache onto the wire until they have determined that they have an actual question.

    Recording would be the creation of a facsimile, which if encoded in RAM as an MP3 or some such, is still a recording. How much is cached at any given moment is not generally known. The phone-home is actually the second copy of the recording, not the first. I imagine somebody has taken one of these apart and looked for the amount of embedded RAM by now and figured out how much they can record, vs how much they say they record.

    The other question is what algo they use for caching. If the cache is a loop, (like a video surveillance system) how long is the loop? Or in other words, how much can they actually download retroactively if they should want to?

    Starting Score:    0  points
    Moderation   +1  
       Interesting=1, Total=1
    Extra 'Interesting' Modifier   0  

    Total Score:   1