Amazon to hand over Echo audio from alleged murder after defendant consents • Hacker News Board

Re: Amazon to hand over Echo audio from alleged murder after defendant consents

#191

Post by Matthias247 » Wed, Mar 08, 2017, 8:13 AM UTC

andrepd wrote: post #151

idanoeman wrote: post #148

Earlier quoted context omitted.

How do you know they don't 1. Listen all the time 2. Use a small neural network on the device to detect when a voice is present 3. Collect this data into one zip file, then send the file when the user says "Alexa", or anything remotely close. They could even put a size limit on the data upload to reduce the variance to prevent you from ever testing whether they do this. Or, they could simply transcribe the audio on t…

Yes, exactly this. They could easily just TTS what you are saying, save the text, and send it together with the rest of the info when you say "Alexa". Thus only sending information when you say "Alexa" but managing to upload all your conversations. I would be very surprised if they aren't doing something like this. The power of analysing which products you talk about in your home more often, what kind of stuff you co…

Nit: TTS is Text To Speech, so you need the other way around :) I most often saw that abbreviated with SDS, although that's also not too correct since a speech dialog system also covers more than only speech recognition.

Re: Amazon to hand over Echo audio from alleged murder after defendant consents

#192

Post by Asooka » Wed, Mar 08, 2017, 8:43 AM UTC

leeoniya wrote: post #149

icebraining wrote: post #28

Earlier quoted context omitted.

Or as cperciva put it, "Playing chicken with cat.jpg" http://www.daemonology.net/blog/2012-01-19-playing-chicken-w...

> In Tarsnap I might take this to an extreme — in addition to the aforementioned encryption, I encourage users to read the tarsnap source code rather than trusting that I got everything right You still have to trust that what's running on your machine and on the servers is compiled directly from the source you have access to, right?

If you build it yourself with the same compiler and options, and get the same bit-exact binary, then it's safe to assume the binary was built from those sources, since infiltrating the compiler team is not an easy job.

Re: Amazon to hand over Echo audio from alleged murder after defendant consents

#193

Post by chatmasta » Wed, Mar 08, 2017, 10:45 AM UTC

ben174 wrote: post #182

danielvf wrote: post #74

Earlier quoted context omitted.

You can just watch the network traffic from the device to see when it is streaming audio. Now this obviously doesn't rule out the device saving stuff locally, but plenty of people have verified that it does generally only send lots of data to the server when you have just asked it to wake up.

It is possible it's doing local voice recognition on all audio, and just sending the text in their payloads. If the content is encrypted, there's no way for any network snooping to determine what they're sending.

This is software... saying there's "no way" is usually incorrect.

For example, you could root the device and disable the encryption.

Or, you could perform experiments in a controlled setting where you play a series of identical recordings to Alexa and measure the statistical similarity in the outgoing data for each. The encryption scheme probably provides more entropy than just the audio, so maybe statistical analysis wouldn't help, but it's a start.

Re: Amazon to hand over Echo audio from alleged murder after defendant consents

#194

Post by HappyTypist » Wed, Mar 08, 2017, 11:05 AM UTC

acomar wrote: post #81

gtirloni wrote: post #2

> after the defendant consented

Why did the defendant's lawyer allow this? I don't understand how this could possibly help the defense.

Most likely Amazo Alan already allowed the defendant to review the data and they've found nothing useful.

Re: Amazon to hand over Echo audio from alleged murder after defendant consents

#195

Post by graphememes » Wed, Mar 08, 2017, 7:15 PM UTC

CaptSpify wrote: post #172

graphememes wrote: post #158

Earlier quoted context omitted.

Actually you can monitor the packets coming through your network and prove whether it is recording or not. Also reverse-engineering the Alexa, and taking it apart will allow you to see whether there is enough storage space for lengthy conversations. Which are only stored for in-transit post the wake-word however. You can delete your recordings on amazon.com and google also allows you to delete your recordings if you…

> So this will give you insight into what recordings they do have. This will give you insight into what recordings they tell you that they have.

Well the culmination of both datasets will allow you to decipher if what they tell you is what you sent.

Re: Amazon to hand over Echo audio from alleged murder after defendant consents

#196

Post by verelo » Wed, Mar 08, 2017, 8:55 PM UTC

andrepd wrote: post #59

verelo wrote: post #44

Earlier quoted context omitted.

Makes me think in future cases when someone says in court "I do not recall", we are going to see Google Home / Echo data being called into play. As someone with 3 google home devices in the house, I feel like my feara I've been suppressing are all coming true.

Then why did you buy 3 Google home devices?

Home automation is an amazingly cool thing to do, and i theorize that it doesn't become a true part of your home unless you remove as many of the barriers to regular use as possible. Voice is very convenient, and access on every floor of the house was therefore something I wanted, so I bought 3.

The experiment is still in progress, but I can tell you they're 90% used for playing music right now :)