Editing Detecting deep-fake audio through vocal tract reconstruction

<section begin=what-is-it />'''[[Detecting deep-fake audio through vocal tract reconstruction]]''' is an epic scientific work, against fake human-like voices, from the [[w:University of Florida]] in published to peers in August 2022. 

[[File:University of Florida logo.svg|thumb|right|'''[https://www.ufl.edu/ University of Florida]''', the home of [https://fics.institute.ufl.edu/ '''Florida Institute for Cybersecurity Research (FICS)''' at fics.institute.ufl.edu], that brought us the [[Detecting deep-fake audio through vocal tract reconstruction]] system to hunt down the fake human-like voices.]]

[[File:Office of Naval Research Official Logo.png|thumb|right|The [https://www.nre.navy.mil/ '''Office of Naval Research''' (ONR) at nre.navy.mil] of the USA funded this breakthrough science.]]

The work [https://www.usenix.org/system/files/sec22fall_blue.pdf '''''Who Are You (I Really Wanna Know)? Detecting Audio DeepFakes Through Vocal Tract Reconstruction''''' at usenix.org], [https://www.usenix.org/conference/usenixsecurity22/presentation/blue presentation page], [https://www.usenix.org/system/files/sec22-blue.pdf version included in the proceedings]<ref name="University of Florida 2022">

{{cite journal
| last1      = Blue
| first1     = Logan
| last2      = Warren
| first2     =  Kevin 
| last3      = Abdullah
| first3     = Hadi 
| last4      = Gibson
| first4     = Cassidy
| last5      = Vargas
| first5     = Luis
| last6      = O’Dell
| first6     = Jessica
| last7      = Butler
| first7     = Kevin 
| last8      = Traynor
| first8     = Patrick      
| date       = August 2022
| title      = Detecting deep-fake audio through vocal tract reconstruction
| url        = https://www.usenix.org/conference/usenixsecurity22/presentation/blue
| journal    = Proceedings of the 31st USENIX Security Symposium
| volume     = 
| issue      = 
| pages      = 2691-2708
| doi        = 
| isbn       = 978-1-939133-31-1
| access-date = 2022-10-06
}}

</ref> and [https://www.usenix.org/system/files/sec22_slides-blue.pdf slides] from researchers of the [https://fics.institute.ufl.edu/ '''Florida Institute for Cybersecurity Research (FICS)''' at fics.institute.ufl.edu] in the [[w:University of Florida]] received funding from the [[w:Office of Naval Research]] and was presented on 2022-08-11 at the 31st [[w:USENIX]] Security Symposium. 

This work was done by PhD student Logan Blue, Kevin Warren, Hadi Abdullah, Cassidy Gibson, Luis Vargas, Jessica O’Dell, Kevin Butler and Professor Patrick Traynor.

The University of Florida Research Foundation Inc has filed for and received an US [https://patents.google.com/patent/US20220036904A1/en patent titled ''''Detecting deep-fake audio through vocal tract reconstruction'''' registration number US20220036904A1 (link to patents.google.com)] with 20 claims. The patent application was published on Thursday 2022-02-03 and approved on 2023-07-04.<section end=what-is-it />
----

== Original reporting ==

<section begin=original-reporting />PhD student Logan Blue and professor Patrick Traynor wrote an article for the general public on the work titled [https://theconversation.com/deepfake-audio-has-a-tell-researchers-use-fluid-dynamics-to-spot-artificial-imposter-voices-189104 '''''Deepfake audio has a tell – researchers use fluid dynamics to spot artificial imposter voices''''' at theconversation.com]<ref name="The Conversation 2022">
{{cite web
|url=https://theconversation.com/deepfake-audio-has-a-tell-researchers-use-fluid-dynamics-to-spot-artificial-imposter-voices-189104
|title=Deepfake audio has a tell – researchers use fluid dynamics to spot artificial imposter voices
|last=Blue
|first=Logan
|last2=Traynor
|first2=Patrick
|date=2022-09-20
|website=theconversation.com
|publisher=[[w:The Conversation (website)]]
|access-date=2022-10-05
|quote=By estimating the anatomy responsible for creating the observed speech, it’s possible to identify the whether the audio was generated by a person or a computer.}}

</ref> that was published Tuesday 2022-09-20 and permanently [[w:copyleft]]ed it under Creative Commons Attribution-NoDerivatives (CC-BY-ND).<section end=original-reporting />

<section begin=embed />
Below is an exact copy of the [https://theconversation.com/deepfake-audio-has-a-tell-researchers-use-fluid-dynamics-to-spot-artificial-imposter-voices-189104 original article] from the [https://stop-synthetic-filth.org/wp/republished/amazing-method-and-results-from-university-of-florida-scientists-in-2022-against-the-menaces-of-digital-sound-alikes-audio-deepfakes/ SSF! wordpress titled "''Amazing method and results from University of Florida scientists in 2022 against the menaces of digital sound-alikes / audio deepfakes''"]. Thank you to the original writers for having the wisdom of licensing the article under CC-BY-ND. 

{{#Widget:Iframe - Amazing method and results from University of Florida scientists in 2022 against the menaces of digital sound-alikes / audio deepfakes}}
<section end=embed />

== Watch ==
{{#lst:Mediatheque|vocal-tract-video}}

----

== Reactions ==
<section begin=reaction />

''' [[User:Juho Kunsola|Juho]]'s reaction '''

{{Q|This is brilliant new science from the University of Florida against the human-like voice-thieving systems in 2022! 👏🏻 👏🏻 👏🏻

Thank you to the University of Florida and their Florida Institute for Cybersecurity Research (FICS) and very warm thank you to the respective scientists for this ground-breaking science against the voice-thieving systems. May ☮️ be with you.

This looks like an awesome start on future automated armor for us humans against the voice-thieving systems!

These methods based on extremely innovative application of existing scientific knowledge and realizing to ask the right questions and the system the University of Florida researchers made to spot the fake synthesized voices and how this system was designed, implemented, tested and found highly effective against the voice-thieving machines of today gives us hope in humanity's struggle to stay humanity despite of the menaces of the synthetic human-like fakes.

This was an issue needing solving, as the digital sound-alikes / audio "deepfakes" / audio "deep fakes" / voice-thieving synthesis systems are known to have been used for crimes since March 2019.
Office of Naval Research funding was a natural source of funding for this innovation, as it is clear that protecting the US Navy and US Marines audio communications networks against any voice-forging adversaries is of high importance.

People who were aware of the voice-thieving-machines problem had been waiting for something and this is more than at least I expected. 🥳 🥳 

Cheers American taxpayers and DoD for funding this breakthrough science!

Please get this technology against the fake voices to humans to protect the humans and humanity! 🫵🏻|[[User:Juho Kunsola|Juho Kunsola]]|[[Detecting deep-fake audio through vocal tract reconstruction]]}}
<section end=reaction />

== See also ==

* Work by Boháček and Farid ''''''[[Protecting President Zelenskyy against deep fakes]]''''''  2022 to protect President Zelensky against [[Synthetic human-like fakes#Digital look-alikes|digital look-alike attacks]]
* Further work by Boháček and Farid ''''''[[Protecting world leaders against deep fakes using facial, gestural, and vocal mannerisms]]'''''' 2022

== External links ==
<section begin=external-links />
* [https://fics.institute.ufl.edu/ '''Florida Institute for Cybersecurity Research (FICS)''' at fics.institute.ufl.edu] in the University of Florida. [https://twitter.com/uf_fics @uf_fics at twitter.com]
* [https://www.usenix.org/ '''The Advanced Computing Systems Association''' at usenix.org] founded in 1975. [https://twitter.com/usenix @usenix at twitter.com] 
* [https://www.nre.navy.mil/ '''Office of Naval Research''' (ONR) at nre.navy.mil] in the USA. [https://twitter.com/USNavyResearch @USNavyResearch at twitter.com] 
<section end=external-links />

== 1st seen in ==
<references group="1st seen in" />

== References ==
<references />

[[Category:Science]]
[[Category:Antifake]]
[[Category:Countermeasure]]
[[Category:2022]]