Open main menu
Home
Random
Recent changes
Special pages
Community portal
Settings
About Stop Synthetic Filth! wiki
Disclaimers
Stop Synthetic Filth! wiki
Search
User menu
Talk
Contributions
Log in
Editing
Synthetic human-like fakes
(section)
Warning:
You are not logged in. Your IP address will be publicly visible if you make any edits. If you
log in
or
create an account
, your edits will be attributed to your username, along with other benefits.
Anti-spam check. Do
not
fill this in!
== 2010's synthetic human-like fakes == * '''2019''' | science and demonstration | At the December 2019 NeurIPS conference, a novel method for making animated fakes of anything with AI [https://aliaksandrsiarohin.github.io/first-order-model-website/ '''''First Order Motion Model for Image Animation''''' (website at aliaksandrsiarohin.github.io)], [https://proceedings.neurips.cc/paper/2019/file/31c0b36aef265d9221af80872ceb62f9-Paper.pdf (paper)] [https://github.com/AliaksandrSiarohin/first-order-model (github)] was presented.<ref group="1st seen in">https://www.technologyreview.com/2020/08/28/1007746/ai-deepfakes-memes/</ref> ** 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''' | US state law | {{#lst:Laws against synthesis and other related crimes|Texas2019}} * '''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 and demonstration | [https://arxiv.org/pdf/1905.09773.pdf ''''Speech2Face: Learning the Face Behind a Voice'''' at arXiv.org] a system for generating likely facial features based on the voice of a person, presented by the [[w:MIT Computer Science and Artificial Intelligence Laboratory]] at the 2019 [[w:Conference on Computer Vision and Pattern Recognition|w:CVPR]]. [https://github.com/saiteja-talluri/Speech2Face Speech2Face at github.com] This may develop to something that really causes problems. [https://neurohive.io/en/news/speech2face-neural-network-predicts-the-face-behind-a-voice/ "Speech2Face: Neural Network Predicts the Face Behind a Voice" reporing at neurohive.io], [https://belitsoft.com/speech-recognition-software-development/speech2face "Speech2Face Sees Voices and Hears Faces: Dreams Come True with AI" reporting at belitsoft.com] * '''2019''' | <font color="red">'''crime'''</font> | '''[[w:Fraud]]''' with [[#digital sound-alikes|digital sound-alike]] technology surfaced in 2019. See [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 or [https://www.forbes.com/sites/jessedamiani/2019/09/03/a-voice-deepfake-was-used-to-scam-a-ceo-out-of-243000/ ''''''A Voice Deepfake Was Used To Scam A CEO Out Of $243,000'''''' at Forbes.com] (2019-09-03) * '''2019''' | demonstration | [http://whichfaceisreal.com/ ''''''Which Face is real?'''''' at whichfaceisreal.com] is an easily unnerving game by [http://ctbergstrom.com/ Carl Bergstrom] and [https://jevinwest.org/ Jevin West] where you need to '''try to distinguish''' from a pair of photos '''which is real and which is not'''. A part of the "tools" of the [https://callingbullshit.org/ Calling Bullshit] course taught at the [[w:University of Washington]]. <font color="green">'''Relevancy: certain'''</font> * '''2019''' | demonstration | '''[https://www.thispersondoesnotexist.com/ 'Thispersondoesnotexist.com']''' (since February 2019) by Philip Wang. It showcases a [[w:StyleGAN]] at the task of making an endless stream of pictures that look like no-one in particular, but are eerily human-like. <font color="green">'''Relevancy: certain'''</font> * '''2019''' | action | [[w:Nvidia]] [[w:open source]]s [[w:StyleGAN]], a novel [[w:generative adversarial network]].<ref name="Medium2019"> {{Cite web |url=https://medium.com/syncedreview/nvidia-open-sources-hyper-realistic-face-generator-stylegan-f346e1a73826 |title= NVIDIA Open-Sources Hyper-Realistic Face Generator StyleGAN |last= |first= |date= 2019-02-09 |website= [[Medium.com]] |access-date= 2020-07-13 }} </ref> * '''<font color="green">2018</font>''' | '''<font color="green">counter-measure</font>''' | In September 2018 Google added “'''involuntary synthetic pornographic imagery'''” to its '''ban list''', allowing anyone to request the search engine block results that falsely depict them as “nude or in a sexually explicit situation.”<ref name="WashingtonPost2018"> {{cite web |url= https://www.washingtonpost.com/technology/2018/12/30/fake-porn-videos-are-being-weaponized-harass-humiliate-women-everybody-is-potential-target/ |title= Fake-porn videos are being weaponized to harass and humiliate women: 'Everybody is a potential target' |last= Harwell |first= Drew |date= 2018-12-30 |website= |publisher= [[w:The Washington Post]] |access-date= 2020-07-13 |quote= In September [of 2018], Google added “involuntary synthetic pornographic imagery” to its ban list }} </ref> '''[https://support.google.com/websearch/answer/9116649?hl=en Information on removing involuntary fake pornography from Google at support.google.com]''' if it shows up in Google and the '''[https://support.google.com/websearch/troubleshooter/3111061#ts=2889054%2C2889099%2C2889064%2C9171203 form to request removing involuntary fake pornography at support.google.com]''', select "''I want to remove: A fake nude or sexually explicit picture or video of myself''" [[File:GoogleLogoSept12015.png|thumb|right|300px|[[w:Google]]'s logo. Google Research demonstrated their '''[https://google.github.io/tacotron/publications/speaker_adaptation/ sound-like-anyone-machine]''' at the '''2018''' [[w:Conference on Neural Information Processing Systems|w:Conference on Neural Information Processing Systems]] (NeurIPS). It requires only 5 seconds of sample to steal a voice.]] * '''<font color="red">2018</font>''' | <font color="red">science</font> and <font color="red">demonstration</font> | The work [http://papers.nips.cc/paper/7700-transfer-learning-from-speaker-verification-to-multispeaker-text-to-speech-synthesis ''''Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis''''] ([https://arxiv.org/abs/1806.04558 at arXiv.org]) was presented at the 2018 [[w:Conference on Neural Information Processing Systems]] ('''NeurIPS'''). The pre-trained model is able to steal voices from a sample of only '''5 seconds''' with almost convincing results. * '''2018''' | science | [https://arxiv.org/abs/1710.10196 '''Progressive Growing of GANs for Improved Quality, Stability, and Variation''' at arxiv.org] ([https://arxiv.org/pdf/1710.10196.pdf .pdf]), colloquially known as ProGANs were presented by Nvidia researchers at the [https://iclr.cc/Conferences/2018 2018 ICLR]. [[w:International Conference on Learning Representations]] * '''2018''' | demonstration | At the 2018 [[w:World Internet Conference]] in [[w:Wuzhen]] the [[w:Xinhua News Agency]] presented two digital look-alikes made to the resemblance of its real news anchors Qiu Hao ([[w:Chinese language]])<ref name="TheGuardian2018"> {{cite web | url = https://www.theguardian.com/world/2018/nov/09/worlds-first-ai-news-anchor-unveiled-in-china | title = World's first AI news anchor unveiled in China | last = Kuo | first = Lily | date = 2018-11-09 | website = | access-date = 2020-07-13 | quote = }} </ref> and Zhang Zhao ([[w:English language]]). The digital look-alikes were made in conjunction with [[w:Sogou]].<ref name="BusinessInsider2018"> {{cite web | url = https://businessinsider.com/ai-news-anchor-created-by-china-xinhua-news-agency-2018-11 | title = China created what it claims is the first AI news anchor — watch it in action here | last = Hamilton | first = Isobel Asher | date = 2018-11-09 | website = | access-date = 2020-07-13 | quote = }} </ref> Neither the [[w:speech synthesis]] used nor the gesturing of the digital look-alike anchors were good enough to deceive the watcher to mistake them for real humans imaged with a TV camera. * '''2018''' | action | [https://schiff.house.gov/imo/media/doc/2018-09%20ODNI%20Deep%20Fakes%20letter.pdf '''Deep Fakes letter to the Office of the Director of National Intelligence''' at schiff.house.gov], a letter sent to the [[w:Director of National Intelligence]] on 2018-09-13 by congresspeople [[w:Adam Schiff]], [[w:Stephanie Murphy]] and [[w:Carlos Curbelo]] requesting a report be compiled on the synthetic human-like fakes situation and what are the threats and what could be the solutions.<ref group="1st seen in">[https://uk.pcmag.com/security/117402/us-lawmakers-ai-generated-fake-videos-may-be-a-security-threat ''''''US Lawmakers: AI-Generated Fake Videos May Be a Security Threat'''''' at uk.pcmag.com], 2018-09-13 reporting by Michael Kan</ref> * '''2018''' | controversy / demonstration | The [[w:deepfake]]s controversy surfaces where [[w:Pornographic film|porn video]]s were doctored utilizing [[w:deep learning|w:deep machine learning]] so that the face of the actress was replaced by the software's opinion of what another persons face would look like in the same pose and lighting. * '''2017''' | science | '''[http://grail.cs.washington.edu/projects/AudioToObama/ 'Synthesizing Obama: Learning Lip Sync from Audio' at grail.cs.washington.edu]'''. In SIGGRAPH 2017 by Supasorn Suwajanakorn et al. of the [[w:University of Washington]] presented an audio driven digital look-alike of upper torso of Barack Obama. It was driven only by a voice track as source data for the animation after the training phase to acquire [[w:lip sync]] and wider facial information from [[w:training material]] consisting 2D videos with audio had been completed.<ref name="Suw2017">{{Citation | last = Suwajanakorn | first = Supasorn | author-link = | last2 = Seitz | first2 = Steven | author2-link = | last3 = Kemelmacher-Shlizerman | first3 = Ira | author3-link = | title = Synthesizing Obama: Learning Lip Sync from Audio | publisher = [[University of Washington]] | year = 2017 | url = http://grail.cs.washington.edu/projects/AudioToObama/ | access-date = 2020-07-13 }} </ref> <font color="green">'''Relevancy: certain'''</font> * '''2016''' | movie | '''[[w:Rogue One]]''' is a Star Wars film for which digital look-alikes of actors [[w:Peter Cushing]] and [[w:Carrie Fisher]] were made. In the film their appearance would appear to be of same age as the actors were during the filming of the original 1977 ''[[w:Star Wars (film)]]'' film. * '''2016''' | science / demonstration | [[w:DeepMind]]'s [[w:WaveNet]] owned by [[w:Google]] also demonstrated ability to steal people's voices [[File:Adobe Corporate Logo.png|thumb|right|300px|[[w:Adobe Inc.]]'s logo. We can thank Adobe for publicly demonstrating their sound-like-anyone-machine in '''2016''' before an implementation was sold to criminal organizations.]] {{#ev:youtube|I3l4XLZ59iw|420px|left|'''''#[[w:Adobe Voco]]. Adobe Audio Manipulator Sneak Peak with [[w:Jordan Peele]]''''' (at Youtube.com). November 2016 demonstration of a Adobe's unreleased sound-like-anyone-machine, the '''[[w:Adobe Voco]]''' at the [[w:Adobe MAX]] 2016 event in [[w:San Diego]], [[w:California]]. The original Adobe Voco '''required 20 minutes of sample''' to '''thieve a voice'''.}} * '''<font color="red">2016</font>''' | <font color="red">science</font> and demonstration | '''[[w:Adobe Inc.]]''' publicly demonstrates '''[[w:Adobe Voco]]''', a '''sound-like-anyone machine''' [https://www.youtube.com/watch?v=I3l4XLZ59iw '#VoCo. Adobe Audio Manipulator Sneak Peak with Jordan Peele | Adobe Creative Cloud' on Youtube]. THe original Adobe Voco required '''20 minutes''' of sample '''to thieve a voice'''. <font color="green">'''Relevancy: certain'''</font>. * '''2016''' | science | '''[http://www.niessnerlab.org/projects/thies2016face.html 'Face2Face: Real-time Face Capture and Reenactment of RGB Videos' at Niessnerlab.org]''' A paper (with videos) on the semi-real-time 2D video manipulation with gesture forcing and lip sync forcing synthesis by Thies et al, Stanford. <font color="green">'''Relevancy: certain'''</font> * '''2016''' | music video | [https://www.youtube.com/watch?v=tMQHAy0HUDo ''''''Plug'''''' by Kube at youtube.com] - A 2016 music video by [[w:Kube (rapper)]] ([[w:fi:Kube]]), that shows deepfake-like technology this early. Video was uploaded on 2016-09-15 and is directed by Faruk Nazeri. * '''2015''' | Science | [https://arxiv.org/abs/1411.7766v3 ''''''Deep Learning Face Attributes in the Wild'''''' at arxiv.org] presented at the 2015 [[w:International Conference on Computer Vision]] * '''2015''' | movie | In the ''[[w:Furious 7]]'' a digital look-alike made of the actor [[w:Paul Walker]] who died in an accident during the filming was done by [[w:Weta Digital]] to enable the completion of the film.<ref name="thr2015"> {{cite web | url = http://www.hollywoodreporter.com/behind-screen/furious-7-how-peter-jacksons-784157 | title = 'Furious 7' and How Peter Jackson's Weta Created Digital Paul Walker | last = Giardina | first = Carolyn | date = 2015-03-25 | work=[[The Hollywood Reporter]] | access-date = 2020-07-13 | quote = }} </ref> * '''2014''' | science | [[w:Ian Goodfellow]] et al. presented the principles of a '''[[w:generative adversarial network]]'''. '''GAN'''s made the headlines in early 2018 with the [[w:deepfake]]s controversies. * '''2013''' | demonstration | At the 2013 SIGGGRAPH [[w:Activision]] and USC presented a [[w:real time computing]] "Digital Ira" a digital face look-alike of Ari Shapiro, an ICT USC research scientist,<ref name="reform_youtube2015"> {{cite AV media | people = | title = ReForm - Hollywood's Creating Digital Clones | medium = youtube | publisher = The Creators Project | location = | date = 2020-07-13 | url = https://www.youtube.com/watch?v=lTC3k9Iv4r0 }} </ref> utilizing the USC light stage X by Ghosh et al. for both reflectance field and motion capture.<ref name="Deb2013">{{cite web | last = Debevec | first = Paul | title = Digital Ira SIGGRAPH 2013 Real-Time Live | website = | date = | url = http://gl.ict.usc.edu/Research/DigitalIra/ | format = | doi = | accessdate = 2017-07-13}} </ref> The end result both precomputed and real-time rendering with the modernest game [[w:Graphics processing unit|w:GPU]] shown [http://gl.ict.usc.edu/Research/DigitalIra/ here] and looks fairly realistic. * '''2013''' | demonstration | A '''[https://ict.usc.edu/pubs/Scanning%20and%20Printing%20a%203D%20Portrait%20of%20President%20Barack%20Obama.pdf 'Scanning and Printing a 3D Portrait of President Barack Obama' at ict.usc.edu]'''. A 7D model and a 3D bust was made of President Obama with his consent. Relevancy: <font color="green">'''Relevancy: certain'''</font> * '''2011''' | <font color="green">'''Law in Finland'''</font> | Distribution and attempt of distribution and also possession of '''synthetic [[w:Child sexual abuse material|CSAM]]''' was '''criminalized''' on Wednesday 2011-06-01, upon the initiative of the [[w:Vanhanen II Cabinet]]. These protections against CSAM were moved into 19 §, 20 § and 21 § of Chapter 20 when the [[Law on sexual offences in Finland 2023]] was improved and gathered into Chapter 20 upon the initiative of the [[w:Marin Cabinet]].
Summary:
Please note that all contributions to Stop Synthetic Filth! wiki are considered to be released under the Creative Commons Attribution-ShareAlike (see
SSF:Copyrights
for details). If you do not want your writing to be edited mercilessly and redistributed at will, then do not submit it here.
You are also promising us that you wrote this yourself, or copied it from a public domain or similar free resource.
Do not submit copyrighted work without permission!
To protect the wiki against automated edit spam, we kindly ask you to solve the following CAPTCHA:
Cancel
Editing help
(opens in new window)