3,839
edits
Synthetic human-like fakes: Difference between revisions
Jump to navigation
Jump to search
→Timeline of synthetic human-like fakes: + 2022 | science and demonstration | w:OpenAI(.com) published w:ChatGPT, a discutational AI accessible with a free account at chat.openai.com. Initial version was published on 2022-11-30.
Juho Kunsola (talk | contribs) (+ Have a listen) |
Juho Kunsola (talk | contribs) (→Timeline of synthetic human-like fakes: + 2022 | science and demonstration | w:OpenAI(.com) published w:ChatGPT, a discutational AI accessible with a free account at chat.openai.com. Initial version was published on 2022-11-30.) |
||
| (34 intermediate revisions by the same user not shown) | |||
| Line 4: | Line 4: | ||
When it cannot be determined by human testing or media forensics whether some fake voice is a synthetic fake of some person's voice, or is it an actual recording made of that person's actual real voice, it is a pre-recorded '''[[Synthetic human-like fakes#Digital sound-alikes|digital sound-alike]]'''. | When it cannot be determined by human testing or media forensics whether some fake voice is a synthetic fake of some person's voice, or is it an actual recording made of that person's actual real voice, it is a pre-recorded '''[[Synthetic human-like fakes#Digital sound-alikes|digital sound-alike]]'''. | ||
::[[Synthetic human-like fakes|Read more about '''synthetic human-like fakes''']], see | ::[[Synthetic human-like fakes|Read more about '''synthetic human-like fakes''']], see and support '''[[organizations and events against synthetic human-like fakes]]''' and what they are doing, what kinds of '''[[Laws against synthesis and other related crimes]]''' have been formulated, [[Synthetic human-like fakes#Timeline of synthetic human-like fakes|examine the SSFWIKI '''timeline''' of synthetic human-like fakes]] or [[Mediatheque|view the '''Mediatheque''']]. | ||
<section end=definitions-of-synthetic-human-like-fakes /> | <section end=definitions-of-synthetic-human-like-fakes /> | ||
| Line 276: | Line 276: | ||
[[File:Spectrogram-19thC.png|thumb|right|640px|A [[w:spectrogram]] of a male voice saying 'nineteenth century']] | [[File:Spectrogram-19thC.png|thumb|right|640px|A [[w:spectrogram]] of a male voice saying 'nineteenth century']] | ||
== Text syntheses == | == Text syntheses == | ||
| Line 353: | Line 340: | ||
* [https://github.com/topics/handwriting-recognition GitHub topic '''handwriting-recognition'''] contains 238 repositories as of September 2021. | * [https://github.com/topics/handwriting-recognition GitHub topic '''handwriting-recognition'''] contains 238 repositories as of September 2021. | ||
== Singing syntheses == | |||
As of 2020 the '''digital sing-alikes''' may not yet be here, but when we hear a faked singing voice and we cannot hear that it is fake, then we will know. An ability to sing does not seem to add much hostile capabilities compared to the ability to thieve spoken word. | |||
* [https://arxiv.org/abs/1910.11690 ''''''Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networks'''''' at arxiv.org], a 2019 singing voice synthesis technique using [[w:convolutional neural network|w:convolutional neural networks (CNN)]]. Accepted into the 2020 [[w:International Conference on Acoustics, Speech, and Signal Processing|International Conference on Acoustics, Speech, and Signal Processing (ICASSP)]]. | |||
* [http://compmus.ime.usp.br/sbcm/2019/papers/sbcm-2019-7.pdf ''''''State of art of real-time singing voice synthesis'''''' at compmus.ime.usp.br] presented at the 2019 [http://compmus.ime.usp.br/sbcm/2019/program/ 17th Brazilian Symposium on Computer Music] | |||
* [http://theses.fr/2017PA066511 ''''''Synthesis and expressive transformation of singing voice'''''' at theses.fr] [https://www.theses.fr/2017PA066511.pdf as .pdf] a 2017 doctorate thesis by [http://theses.fr/227185943 Luc Ardaillon] | |||
* [http://mtg.upf.edu/node/512 ''''''Synthesis of the Singing Voice by Performance Sampling and Spectral Models'''''' at mtg.upf.edu], a 2007 journal article in the [[w:IEEE Signal Processing Society]]'s Signal Processing Magazine | |||
* [https://www.researchgate.net/publication/4295714_Speech-to-Singing_Synthesis_Converting_Speaking_Voices_to_Singing_Voices_by_Controlling_Acoustic_Features_Unique_to_Singing_Voices ''''''Speech-to-Singing Synthesis: Converting Speaking Voices to Singing Voices by Controlling Acoustic Features Unique to Singing Voices'''''' at researchgate.net], a November 2007 paper published in the IEEE conference on Applications of Signal Processing to Audio and Acoustics | |||
* [[w:Category:Singing software synthesizers]] | |||
---- | |||
= Timeline of synthetic human-like fakes = | = Timeline of synthetic human-like fakes = | ||
| Line 358: | Line 360: | ||
== 2020's synthetic human-like fakes == | == 2020's synthetic human-like fakes == | ||
* '''2022''' | <font color="orange">'''science'''</font> and <font color="green">'''demonstration'''</font> | [[w:OpenAI]][https://openai.com/ (.com)] published [[w:ChatGPT]], a discutational AI accessible with a free account at [https://chat.openai.com/ chat.openai.com]. Initial version was published on 2022-11-30. | |||
* '''2022''' | '''<font color="green">brief report of counter-measures</font>''' | {{#lst:Protecting world leaders against deep fakes using facial, gestural, and vocal mannerisms|what-is-it}} Publication date 2022-11-23. | |||
* '''2022''' | '''<font color="green">counter-measure</font>''' | {{#lst:Who Are You (I Really Wanna Know)? Detecting Audio DeepFakes Through Vocal Tract Reconstruction|what-is-it}} | |||
:{{#lst:Who Are You (I Really Wanna Know)? Detecting Audio DeepFakes Through Vocal Tract Reconstruction|original-reporting}}. Presented to peers in August 2022 and to the general public in September 2022. | |||
* '''2022''' | '''<font color="green">counter-measure</font>''' | {{#lst:Protecting President Zelenskyy against deep fakes|what-is-it}} Preprint published in February 2022 and submitted to [[w:arXiv]] in June 2022 | |||
* '''2022''' | '''<font color="green">science / review of counter-measures</font>''' | [https://www.mdpi.com/1999-4893/15/5/155 ''''''A Review of Modern Audio Deepfake Detection Methods: Challenges and Future Directions'''''' at mdpi.com]<ref name="Audio Deepfake detection review 2022"> | |||
{{cite journal | |||
| last1 = Almutairi | |||
| first1 = Zaynab | |||
| last2 = Elgibreen | |||
| first2 = Hebah | |||
| date = 2022-05-04 | |||
| title = A Review of Modern Audio Deepfake Detection Methods: Challenges and Future Directions | |||
| url = https://www.mdpi.com/1999-4893/15/5/155 | |||
| journal = [[w:Algorithms (journal)]] | |||
| volume = | |||
| issue = | |||
| pages = | |||
| doi = https://doi.org/10.3390/a15050155 | |||
| access-date = 2022-10-18 | |||
}} | |||
</ref>, a review of audio deepfake detection methods by researchers Zaynab Almutairi and Hebah Elgibreen of the [[w:King Saud University]], Saudi Arabia published in [[w:Algorithms (journal)]] on Wednesday 2022-05-04 published by the [[w:MDPI]] (Multidisciplinary Digital Publishing Institute). This article belongs to the Special Issue [https://www.mdpi.com/journal/algorithms/special_issues/Adversarial_Federated_Machine_Learning ''Commemorative Special Issue: Adversarial and Federated Machine Learning: State of the Art and New Perspectives'' at mdpi.com] | |||
* '''2022''' | '''<font color="green">science / counter-measure</font>''' | [https://arxiv.org/abs/2203.15563 ''''''Attacker Attribution of Audio Deepfakes'''''' at arxiv.org], a pre-print was presented at the [https://www.interspeech2022.org/ Interspeech 2022 conference] organized by [[w:International Speech Communication Association]] in Korea September 18-22 2022. | |||
* '''2021''' | Science and demonstration | In the NeurIPS 2021 held virtually in December researchers from Nvidia and [[w:Aalto University]] present their paper [https://nvlabs.github.io/stylegan3/ '''''Alias-Free Generative Adversarial Networks (StyleGAN3)''''' at nvlabs.github.io] and associated [https://github.com/NVlabs/stylegan3 implementation] in [[w:PyTorch]] and the results are deceivingly human-like in appearance. [https://nvlabs-fi-cdn.nvidia.com/stylegan3/stylegan3-paper.pdf StyleGAN3 paper as .pdf at nvlabs-fi-cdn.nvidia.com] | * '''2021''' | Science and demonstration | In the NeurIPS 2021 held virtually in December researchers from Nvidia and [[w:Aalto University]] present their paper [https://nvlabs.github.io/stylegan3/ '''''Alias-Free Generative Adversarial Networks (StyleGAN3)''''' at nvlabs.github.io] and associated [https://github.com/NVlabs/stylegan3 implementation] in [[w:PyTorch]] and the results are deceivingly human-like in appearance. [https://nvlabs-fi-cdn.nvidia.com/stylegan3/stylegan3-paper.pdf StyleGAN3 paper as .pdf at nvlabs-fi-cdn.nvidia.com] | ||
| Line 368: | Line 401: | ||
|last=Rosner | |last=Rosner | ||
|first=Helen | |first=Helen | ||
|author-link=Helen Rosner | |author-link=[[w:Helen Rosner]] | ||
|date=2021-07-15 | |date=2021-07-15 | ||
|title=A Haunting New Documentary About Anthony Bourdain | |title=A Haunting New Documentary About Anthony Bourdain | ||
| Line 385: | Line 418: | ||
* '''2021''' | '''<font color="red">crime / fraud</font>''' | {{#lst:Synthetic human-like fakes|2021 digital sound-alike enabled fraud}} | * '''2021''' | '''<font color="red">crime / fraud</font>''' | {{#lst:Synthetic human-like fakes|2021 digital sound-alike enabled fraud}} | ||
* '''<font color="green">2020</font>''' | '''<font color="green">counter-measure</font>''' | | * '''<font color="green">2020</font>''' | '''<font color="green">counter-measure</font>''' | The [https://incidentdatabase.ai/ ''''''AI Incident Database'''''' at incidentdatabase.ai] was introduced on 2020-11-18 by the [[w:Partnership on AI]].<ref name="PartnershipOnAI2020">https://www.partnershiponai.org/aiincidentdatabase/</ref> | ||
[[File:Appearance of Queen Elizabeth II stolen by Channel 4 in Dec 2020 (screenshot at 191s).png|thumb|right|480px|In Dec 2020 Channel 4 aired a Queen-like fake i.e. they had thieved the appearance of Queen Elizabeth II using deepfake methods.]] | |||
* '''2020''' | '''Controversy''' / '''Public service announcement''' | Channel 4 thieved the appearance of Queen Elizabeth II using deepfake methods. The product of synthetic human-like fakery originally aired on Channel 4 on 25 December at 15:25 GMT.<ref name="Queen-like deepfake 2020 BBC reporting">https://www.bbc.com/news/technology-55424730</ref> [https://www.youtube.com/watch?v=IvY-Abd2FfM&t=3s View in YouTube] | |||
* '''2020''' | reporting | [https://www.wired.co.uk/article/deepfake-porn-websites-videos-law "''Deepfake porn is now mainstream. And major sites are cashing in''" at wired.co.uk] by Matt Burgess. Published August 2020. | * '''2020''' | reporting | [https://www.wired.co.uk/article/deepfake-porn-websites-videos-law "''Deepfake porn is now mainstream. And major sites are cashing in''" at wired.co.uk] by Matt Burgess. Published August 2020. | ||
| Line 392: | Line 429: | ||
** [https://www.cnet.com/news/mit-releases-deepfake-video-of-nixon-announcing-nasa-apollo-11-disaster/ Cnet.com July 2020 reporting ''MIT releases deepfake video of 'Nixon' announcing NASA Apollo 11 disaster''] | ** [https://www.cnet.com/news/mit-releases-deepfake-video-of-nixon-announcing-nasa-apollo-11-disaster/ Cnet.com July 2020 reporting ''MIT releases deepfake video of 'Nixon' announcing NASA Apollo 11 disaster''] | ||
* '''2020''' | US state law | {{#lst:Laws against | * '''2020''' | US state law | {{#lst:Laws against synthesis and other related crimes|California2020}} | ||
* '''2020''' | Chinese legislation | {{#lst:Laws against | * '''2020''' | Chinese legislation | {{#lst:Laws against synthesis and other related crimes|China2020}} | ||
== 2010's synthetic human-like fakes == | == 2010's synthetic human-like fakes == | ||
| Line 399: | Line 436: | ||
** Reporting [https://www.technologyreview.com/2020/08/28/1007746/ai-deepfakes-memes/ '''''Memers are making deepfakes, and things are getting weird''''' at technologyreview.com], 2020-08-28 by Karen Hao. | ** Reporting [https://www.technologyreview.com/2020/08/28/1007746/ai-deepfakes-memes/ '''''Memers are making deepfakes, and things are getting weird''''' at technologyreview.com], 2020-08-28 by Karen Hao. | ||
* '''2019''' | demonstration | In September 2019 [[w:Yle]], the Finnish [[w:public broadcasting company]], aired a result of experimental [[w:journalism]], [https://yle.fi/uutiset/3-10955498 '''a deepfake of the President in office'''] [[w:Sauli Niinistö]] in its main news broadcast for the purpose of highlighting the advancing disinformation technology and problems that arise from it. | * '''2019''' | demonstration | In September 2019 [[w:Yle]], the Finnish [[w:public broadcasting company]], aired a result of experimental [[w:journalism]], [https://yle.fi/uutiset/3-10955498 '''a deepfake of the President in office'''] [[w:Sauli Niinistö]] in its main news broadcast for the purpose of highlighting the advancing disinformation technology and problems that arise from it. | ||
* '''2019''' | US state law | {{#lst:Laws against | * '''2019''' | US state law | {{#lst:Laws against synthesis and other related crimes|Texas2019}} | ||
* '''2019''' | US state law | {{#lst:Laws against | * '''2019''' | US state law | {{#lst:Laws against synthesis and other related crimes|Virginia2019}} | ||
* '''2019''' | Science | [https://arxiv.org/pdf/1809.10460.pdf '''''Sample Efficient Adaptive Text-to-Speech''''' .pdf at arxiv.org], a 2019 paper from Google researchers, published as a conference paper at [[w:International Conference on Learning Representations]] (ICLR)<ref group="1st seen in" name="ConnectedPapers suggestion on Google Transfer learning 2018"> https://www.connectedpapers.com/main/8fc09dfcff78ac9057ff0834a83d23eb38ca198a/Transfer-Learning-from-Speaker-Verification-to-Multispeaker-TextToSpeech-Synthesis/graph</ref> | * '''2019''' | Science | [https://arxiv.org/pdf/1809.10460.pdf '''''Sample Efficient Adaptive Text-to-Speech''''' .pdf at arxiv.org], a 2019 paper from Google researchers, published as a conference paper at [[w:International Conference on Learning Representations]] (ICLR)<ref group="1st seen in" name="ConnectedPapers suggestion on Google Transfer learning 2018"> https://www.connectedpapers.com/main/8fc09dfcff78ac9057ff0834a83d23eb38ca198a/Transfer-Learning-from-Speaker-Verification-to-Multispeaker-TextToSpeech-Synthesis/graph</ref> | ||
| Line 583: | Line 620: | ||
* <font color="red">'''1999'''</font> | <font color="red">'''institute founded'''</font> | The '''[[w:Institute for Creative Technologies]]''' was founded by the [[w:United States Army]] in the [[w:University of Southern California]]. It collaborates with the [[w:United States Army Futures Command]], [[w:United States Army Combat Capabilities Development Command]], [[w:Combat Capabilities Development Command Soldier Center]] and [[w:United States Army Research Laboratory]].<ref name="ICT-about">https://ict.usc.edu/about/</ref>. In 2016 [[w:Hao Li]] was appointed to direct the institute. | * <font color="red">'''1999'''</font> | <font color="red">'''institute founded'''</font> | The '''[[w:Institute for Creative Technologies]]''' was founded by the [[w:United States Army]] in the [[w:University of Southern California]]. It collaborates with the [[w:United States Army Futures Command]], [[w:United States Army Combat Capabilities Development Command]], [[w:Combat Capabilities Development Command Soldier Center]] and [[w:United States Army Research Laboratory]].<ref name="ICT-about">https://ict.usc.edu/about/</ref>. In 2016 [[w:Hao Li]] was appointed to direct the institute. | ||
* '''1997''' | '''technology / science''' | [https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/human/bregler-sig97.pdf ''''Video rewrite: Driving visual speech with audio'''' at www2.eecs.berkeley.edu]<ref name="Bregler1997"> | |||
{{cite journal | |||
| last1 = Bregler | |||
| first1 = Christoph | |||
| last2 = Covell | |||
| first2 = Michele | |||
| last3 = Slaney | |||
| first3 = Malcolm | |||
| date = 1997-08-03 | |||
| title = Video Rewrite: Driving Visual Speech with Audio | |||
| url = https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/human/bregler-sig97.pdf | |||
| journal = SIGGRAPH '97: Proceedings of the 24th annual conference on Computer graphics and interactive techniques | |||
| volume = | |||
| issue = | |||
| pages = 353-360 | |||
| doi = 10.1145/258734.258880 | |||
| access-date = 2022-09-09 | |||
}} | |||
</ref><ref group="1st seen in" name="Bohacek-Farid-2022"> | |||
PROTECTING PRESIDENT ZELENSKYY AGAINST DEEP FAKES https://arxiv.org/pdf/2206.12043.pdf | |||
</ref> Christoph Breigler, Michelle Covell and Malcom Slaney presented their work at the ACM SIGGRAPH 1997. [https://www.dropbox.com/sh/s4l00z7z4gn7bvo/AAAP5oekFqoelnfZYjS8NQyca?dl=0 Download video evidence of ''Video rewrite: Driving visual speech with audio'' Bregler et al 1997 from dropbox.com], [http://chris.bregler.com/videorewrite/ view author's site at chris.bregler.com], [https://dl.acm.org/doi/10.1145/258734.258880 paper at dl.acm.org] [https://www.researchgate.net/publication/220720338_Video_Rewrite_Driving_Visual_Speech_with_Audio paper at researchgate.net] | |||
* '''1994''' | movie | [[w:The Crow (1994 film)]] was the first film production to make use of [[w:digital compositing]] of a computer simulated representation of a face onto scenes filmed using a [[w:body double]]. Necessity was the muse as the actor [[w:Brandon Lee]] portraying the protagonist was tragically killed accidentally on-stage. | * '''1994''' | movie | [[w:The Crow (1994 film)]] was the first film production to make use of [[w:digital compositing]] of a computer simulated representation of a face onto scenes filmed using a [[w:body double]]. Necessity was the muse as the actor [[w:Brandon Lee]] portraying the protagonist was tragically killed accidentally on-stage. | ||