3,839
edits
Synthetic human-like fakes: Difference between revisions
m
adjust heading levels
Juho Kunsola (talk | contribs) (major reorg of the media) |
Juho Kunsola (talk | contribs) m (adjust heading levels) |
||
| Line 15: | Line 15: | ||
Image 2 by Blanz and Vettel – Copyright ACM 1999 – http://dl.acm.org/citation.cfm?doid=311535.311556 – Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page.]] | Image 2 by Blanz and Vettel – Copyright ACM 1999 – http://dl.acm.org/citation.cfm?doid=311535.311556 – Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page.]] | ||
= Digital look-alikes = | == Digital look-alikes == | ||
{{#ev:vimeo|16292363|640px|right|''[[w:A Computer Animated Hand|A Computer Animated Hand]]'' is a 1972 short film by [[w:Edwin Catmull|Edwin Catmull]] and [[w:Fred Parke|Fred Parke]]. This was the first time that [[w:computer-generated imagery|computer-generated imagery]] was used in film to animate likenesses of moving human appearance.}} | {{#ev:vimeo|16292363|640px|right|''[[w:A Computer Animated Hand|A Computer Animated Hand]]'' is a 1972 short film by [[w:Edwin Catmull|Edwin Catmull]] and [[w:Fred Parke|Fred Parke]]. This was the first time that [[w:computer-generated imagery|computer-generated imagery]] was used in film to animate likenesses of moving human appearance.}} | ||
== Introduction to digital look-alikes == | === Introduction to digital look-alikes === | ||
[[File:The-diffuse-reflection-deducted-from-the-specular-reflection-Debevec-2000.png|thumb|right|260px|Subtraction of the diffuse reflection from the specular reflection yields the specular component of the model's reflectance. | [[File:The-diffuse-reflection-deducted-from-the-specular-reflection-Debevec-2000.png|thumb|right|260px|Subtraction of the diffuse reflection from the specular reflection yields the specular component of the model's reflectance. | ||
| Line 46: | Line 46: | ||
{{Q|Do you think that was [[w:Hugo Weaving|Hugo Weaving]]'s left cheekbone that [[w:Keanu Reeves|Keanu Reeves]] punched in with his right fist?|Trad|The Matrix Revolutions}} | {{Q|Do you think that was [[w:Hugo Weaving|Hugo Weaving]]'s left cheekbone that [[w:Keanu Reeves|Keanu Reeves]] punched in with his right fist?|Trad|The Matrix Revolutions}} | ||
== The problems with digital look-alikes == | === The problems with digital look-alikes === | ||
[[File:Deb-2000-reflectance-separation.png|thumb|360px|right|Image 1: Separating specular and diffuse reflected light | [[File:Deb-2000-reflectance-separation.png|thumb|360px|right|Image 1: Separating specular and diffuse reflected light | ||
| Line 69: | Line 69: | ||
---- | ---- | ||
= Digital sound-alikes = | == Digital sound-alikes == | ||
Living people can defend¹ themselves against digital sound-alike by denying the things the digital sound-alike says if they are presented to the target, but dead people cannot. Digital sound-alikes offer criminals new disinformation attack vectors and wreak havoc on provability. | Living people can defend¹ themselves against digital sound-alike by denying the things the digital sound-alike says if they are presented to the target, but dead people cannot. Digital sound-alikes offer criminals new disinformation attack vectors and wreak havoc on provability. | ||
== Timeline of digital sound-alikes == | === Timeline of digital sound-alikes === | ||
* In '''2016''' [[w:Adobe Inc.]]'s [[w:Adobe Voco|Voco]], an unreleased prototype, was publicly demonstrated in 2016. ([https://www.youtube.com/watch?v=I3l4XLZ59iw&t=5s View and listen to Adobe MAX 2016 presentation of Voco]) | * In '''2016''' [[w:Adobe Inc.]]'s [[w:Adobe Voco|Voco]], an unreleased prototype, was publicly demonstrated in 2016. ([https://www.youtube.com/watch?v=I3l4XLZ59iw&t=5s View and listen to Adobe MAX 2016 presentation of Voco]) | ||
| Line 87: | Line 87: | ||
---- | ---- | ||
== Examples of speech synthesis software not quite able to fool a human yet == | === Examples of speech synthesis software not quite able to fool a human yet === | ||
Some other contenders to create digital sound-alikes are though, as of 2019, their speech synthesis in most use scenarios does not yet fool a human because the results contain tell tale signs that give it away as a speech synthesizer. | Some other contenders to create digital sound-alikes are though, as of 2019, their speech synthesis in most use scenarios does not yet fool a human because the results contain tell tale signs that give it away as a speech synthesizer. | ||
| Line 95: | Line 95: | ||
== Documented digital sound-alike attacks == | === Documented digital sound-alike attacks === | ||
* [https://www.washingtonpost.com/technology/2019/09/04/an-artificial-intelligence-first-voice-mimicking-software-reportedly-used-major-theft/?noredirect=on 'An artificial-intelligence first: Voice-mimicking software reportedly used in a major theft'], a 2019 Washington Post article | * [https://www.washingtonpost.com/technology/2019/09/04/an-artificial-intelligence-first-voice-mimicking-software-reportedly-used-major-theft/?noredirect=on 'An artificial-intelligence first: Voice-mimicking software reportedly used in a major theft'], a 2019 Washington Post article | ||
---- | ---- | ||
== Example of a hypothetical digital sound-alike attack == | === Example of a hypothetical 4-victim digital sound-alike attack === | ||
A very simple example of a digital sound-alike attack is as follows: | A very simple example of a digital sound-alike attack is as follows: | ||
| Line 116: | Line 116: | ||
---- | ---- | ||
== 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis' 2018 by Google Research == | === Transclusion: 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis' 2018 by Google Research === | ||
The Iframe below is transcluded from [https://google.github.io/tacotron/publications/speaker_adaptation/ 'Audio samples from "Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis"' at google.gituhub.io], the audio samples of a sound-like-anyone machine presented as at the 2018 [[w:NeurIPS]] conference by Google researchers. | The Iframe below is transcluded from [https://google.github.io/tacotron/publications/speaker_adaptation/ 'Audio samples from "Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis"' at google.gituhub.io], the audio samples of a sound-like-anyone machine presented as at the 2018 [[w:NeurIPS]] conference by Google researchers. | ||
| Line 126: | Line 126: | ||
[[File:Spectrogram-19thC.png|thumb|right|640px|A [[w:spectrogram|spectrogram]] of a male voice saying 'nineteenth century']] | [[File:Spectrogram-19thC.png|thumb|right|640px|A [[w:spectrogram|spectrogram]] of a male voice saying 'nineteenth century']] | ||
= Footnotes = | == Footnotes == | ||
<references group="footnote" /> | <references group="footnote" /> | ||
= References = | == References == | ||
<references /> | <references /> | ||