Re Inaudible Voice Commands: The Long-Range Attack and Defense | USENIX

["Dave Farber" <farber () gmail com>]

Begin forwarded message:

> From: Jonathan Levine <jonathan.canuck.levine () gmail com>
> Date: April 11, 2018 at 12:42:10 PM EDT
> To: dave () farber net
> Subject: Re: [IP] Inaudible Voice Commands: The Long-Range Attack and Defense | USENIX
>
> Dave:
>
> For IP, if you wish.
>
> It isn't just "recent work" that's concentrated on the use of inaudible
> signals in acoustic environments.  For many years, Arbitron has
> been manufacturing systems for tracking TV and radio audience
> habits.  Their hardware is installed at the broadcaster's head end
> and injects unique "subaudible" (their term) identifiers into the
> audio signal stream that aren't perceived by the listeners/viewers.
> Participants in this survey (as was my family for a few years, for the
> Canadian "Bureau of Broadcast Measurement" (BBM)) wear little
> pager-sized DSP dataloggers, parking them at night in a charger/
> modem that sends the stats home every night.
>
> Interestingly, broadcasters participate by installing the head-end
> hardware even if they don't pay BBM for the resulting listener stats.
> At least, that's the case with CJSW (University of Calgary), the
> station that I've been affiliated with since 1980.
>
> Jonathan
>
> > On 4/9/18, Dave Farber <farber () gmail com> wrote:
> >
> > https://www.usenix.org/conference/nsdi18/presentation/roy
> >
> > Inaudible Voice Commands: The Long-Range Attack and Defense
> > Authors:
> >
> > Nirupam Roy, Sheng Shen, Haitham Hassanieh, and Romit Roy Choudhury,
> > University of Illinois at Urbana-Champaign
> >
> > Abstract:
> >
> > Recent work has shown that inaudible signals (at ultrasound frequencies) can
> > be designed in a way that they become audible to microphones. Designed well,
> > this can empower an adversary to stand on the road and silently control
> > Amazon Echo and Google Home-like devices in people’s homes. A voice command
> > like "Alexa, open the garage door" can be a serious threat.
> >
> > While recent work has demonstrated feasibility, two issues remain open: (1)
> > The attacks can only be launched from within 5 ft of Amazon Echo, and
> > increasing this range makes the attack audible. (2) There is no clear
> > solution against these ultrasound attacks, since they exploit a recently
> > discovered loophole in hardware non-linearity.
> >
> > This paper is an attempt to close both these gaps. We begin by developing an
> > attack that achieves 25 ft range, limited by the power of our amplifier. We
> > then develop a defense against this class of voice attacks that exploit
> > non-linearity. Our core ideas emerge from a careful forensics on voice,
> >     , finding indelible traces of nonlinearity in recorded voice signals.
> > Our system, LipRead, demonstrates the inaudible attack in various
> > conditions, followed by defenses that only require software changes to the
> > microphone.



-------------------------------------------
Archives: https://www.listbox.com/member/archive/247/=now
Modify Your Subscription: https://www.listbox.com/member/?member_id=18849915&id_secret=18849915-aa268125
Unsubscribe Now: 
https://www.listbox.com/unsubscribe/?member_id=18849915&id_secret=18849915-32545cb4&post_id=20180411171914:FA46B564-3DCD-11E8-BA21-CC36E8F62934
Powered by Listbox: http://www.listbox.com