Fake videos of real people -- and how to spot them | Supasorn Suwajanakorn

1,286,872 views ・ 2018-07-25

TED


Please double-click on the English subtitles below to play the video.

Prevodilac: Stevan Stanišić Lektor: Tijana Mihajlović
00:12
Look at these images.
0
12876
1151
Pogledajte ove slike.
00:14
Now, tell me which Obama here is real.
1
14051
2635
A sad, recite mi koji Obama je pravi.
00:16
(Video) Barack Obama: To help families refinance their homes,
2
16710
2861
(Video) Barak Obama: Da pomognemo porodicama s refinansiranjem domova,
00:19
to invest in things like high-tech manufacturing,
3
19595
2647
da uložimo u stvari kao što su visoko-tehnološka proizvodnja,
00:22
clean energy
4
22266
1159
čista energija i infrastruktura koja stvara dobre nove poslove.
00:23
and the infrastructure that creates good new jobs.
5
23449
2779
00:26
Supasorn Suwajanakorn: Anyone?
6
26647
1484
Supasorn Suvanjakorn: Bilo ko?
00:28
The answer is none of them.
7
28155
1874
Odgovor je: nijedan od njih.
00:30
(Laughter)
8
30053
1114
(Smeh)
00:31
None of these is actually real.
9
31191
1786
Nijedan od ovih zapravo nije pravi.
Dozvolite da objasnim kako smo dospeli ovde.
00:33
So let me tell you how we got here.
10
33001
1840
00:35
My inspiration for this work
11
35940
1578
Moja inspiracija za ovaj posao bio je projekat
00:37
was a project meant to preserve our last chance for learning about the Holocaust
12
37542
5411
namenjen očuvanju naše poslednje šanse za saznanje o holokaustu od preživelih.
00:42
from the survivors.
13
42977
1768
00:44
It's called New Dimensions in Testimony,
14
44769
2627
Zove se „Nove dimenzije u svedočenju“
00:47
and it allows you to have interactive conversations
15
47420
3126
i dozvoljava vam da vodite interaktivne razgovore
00:50
with a hologram of a real Holocaust survivor.
16
50570
2556
sa hologramom pravog preživelog iz holokausta.
00:53
(Video) Man: How did you survive the Holocaust?
17
53793
1966
(Video) Čovek: Kako ste preživeli holokaust?
00:55
(Video) Hologram: How did I survive?
18
55783
1668
(Video) Hologram: Kako sam preživeo?
00:57
I survived,
19
57912
1807
Preživeo sam,
01:00
I believe,
20
60419
1527
verujem,
01:01
because providence watched over me.
21
61970
3023
zato što je proviđenje bdelo nada mnom.
01:05
SS: Turns out these answers were prerecorded in a studio.
22
65573
3454
SS: Ispostavlja se da su ovi odgovori unapred snimljeni u studiju.
01:09
Yet the effect is astounding.
23
69051
2452
Pa ipak, efekat je zapanjujuć.
01:11
You feel so connected to his story and to him as a person.
24
71527
3619
Osećate se privrženo njegovoj priči i njemu kao osobi.
01:16
I think there's something special about human interaction
25
76011
3301
Mislim da postoji nešto posebno u vezi sa ljudskom interakcijom
01:19
that makes it much more profound
26
79336
2757
što je čini mnogo dubljom
01:22
and personal
27
82117
2198
i ličnijom
01:24
than what books or lectures or movies could ever teach us.
28
84339
3485
nego što bi knjige, predavanja ili filmovi ikada mogli da nas nauče.
01:28
So I saw this and began to wonder,
29
88267
2425
Dakle, video sam ovo i počeo da se pitam:
01:30
can we create a model like this for anyone?
30
90716
2810
da li možemo da napravimo ovakav model za bilo koga?
01:33
A model that looks, talks and acts just like them?
31
93550
2975
Model koji izgleda, priča i ponaša se baš kao oni?
01:37
So I set out to see if this could be done
32
97573
2007
Pokrenuo sam se da vidim da li je izvodljivo
01:39
and eventually came up with a new solution
33
99604
2310
i naposletku došao do novog rešenja
01:41
that can build a model of a person using nothing but these:
34
101938
3220
koje može da napravi model osobe koristeći ništa drugo osim ovoga:
01:45
existing photos and videos of a person.
35
105747
2214
postojećih fotografija i snimaka osobe.
01:48
If you can leverage this kind of passive information,
36
108701
2617
Ako možete da iskoristite ovu vrstu pasivnih informacija,
01:51
just photos and video that are out there,
37
111342
2007
samo dostupne fotografije i snimke,
01:53
that's the key to scaling to anyone.
38
113373
2056
to je ključno za primenu na svakoga.
01:56
By the way, here's Richard Feynman,
39
116119
1777
Uzgred, evo Ričarda Fajnmana,
01:57
who in addition to being a Nobel Prize winner in physics
40
117920
3413
ko je uz to što je osvojio Nobelovu nagradu za fiziku,
02:01
was also known as a legendary teacher.
41
121357
2453
takođe bio poznat kao legendaran predavač.
02:05
Wouldn't it be great if we could bring him back
42
125080
2198
Zar ne bi bilo sjajno kada bismo mogli da ga vratimo
02:07
to give his lectures and inspire millions of kids,
43
127302
3265
da drži svoja predavanja i inspiriše milione klinaca,
02:10
perhaps not just in English but in any language?
44
130591
2992
možda čak ne samo na engleskom, već na bilo kom jeziku?
02:14
Or if you could ask our grandparents for advice and hear those comforting words
45
134441
4602
Ili ako biste mogli da pitate naše bake i deke za savet i čujete utešne reči
02:19
even if they're no longer with us?
46
139067
1770
čak i ako više nisu s nama?
02:21
Or maybe using this tool, book authors, alive or not,
47
141683
3396
Ili bi možda korišćenjem ovog alata pisci knjiga, živi ili ne,
02:25
could read aloud all of their books for anyone interested.
48
145103
2937
naglas mogli da čitaju sve svoje knjige za sve zainteresovane.
02:29
The creative possibilities here are endless,
49
149199
2437
Kreativne mogućnosti za ovo su beskrajne,
02:31
and to me, that's very exciting.
50
151660
1713
i za mene, to je vrlo uzbudljivo.
02:34
And here's how it's working so far.
51
154595
2002
A evo kako to radi za sad.
02:36
First, we introduce a new technique
52
156621
1667
Prvo, uvodimo novu tehniku
02:38
that can reconstruct a high-detailed 3D face model from any image
53
158312
4572
koja može da rekonstruiše veoma detaljan 3D model lica
sa bilo koje slike,
02:42
without ever 3D-scanning the person.
54
162908
2119
bez ikakvog 3D skeniranja osobe.
02:45
And here's the same output model from different views.
55
165890
2642
Evo istog izlaznog modela iz različitih uglova.
02:49
This also works on videos,
56
169969
1502
Ovo funkcioniše i na snimcima,
02:51
by running the same algorithm on each video frame
57
171495
2852
korišćenjem istog algoritma na svakoj slici snimka
02:54
and generating a moving 3D model.
58
174371
2222
i generisanjem pokretnog 3D modela.
02:57
And here's the same output model from different angles.
59
177538
2772
Evo istog izlaznog modela iz različitih uglova.
03:01
It turns out this problem is very challenging,
60
181933
2534
Ispostavlja se da je ovo veoma problematično,
03:04
but the key trick is that we are going to analyze
61
184491
2525
ali ključni trik leži u tome
da ćemo unapred analizirati veliku zbirku fotografija osobe.
03:07
a large photo collection of the person beforehand.
62
187040
2966
03:10
For George W. Bush, we can just search on Google,
63
190650
2539
Za Džordža V. Buša možemo prosto da potražimo na Guglu
03:14
and from that, we are able to build an average model,
64
194309
2499
i iz toga, u stanju smo da napravimo prosečan model,
03:16
an iterative, refined model to recover the expression
65
196832
3111
iterativan, prerađen model
da povratimo izraz u finim detaljima, kao što su brazde i bore.
03:19
in fine details, like creases and wrinkles.
66
199967
2336
03:23
What's fascinating about this
67
203326
1403
Ono što je fascinantno kod ovoga je
03:24
is that the photo collection can come from your typical photos.
68
204753
3423
da zbirka fotografija može nastati od vaših tipičnih fotografija.
03:28
It doesn't really matter what expression you're making
69
208200
2603
Nije stvarno bitno kakav izraz imate
03:30
or where you took those photos.
70
210827
1885
ili gde ste snimili fotografije.
03:32
What matters is that there are a lot of them.
71
212736
2400
Ono što je bitno je da ih ima mnogo.
03:35
And we are still missing color here,
72
215160
1736
A ovde nam još uvek fali boja,
03:36
so next, we develop a new blending technique
73
216920
2348
pa dalje razvijamo novu tehniku mešanja
03:39
that improves upon a single averaging method
74
219292
2836
koja koristi samo jednu metodu uprosečavanja
03:42
and produces sharp facial textures and colors.
75
222152
2818
i proizvodi jasne teksture lica i boje.
03:45
And this can be done for any expression.
76
225779
2771
A ovo može da se uradi za bilo koji izraz.
03:49
Now we have a control of a model of a person,
77
229485
2499
Sada imamo kontrolu nad modelom osobe,
03:52
and the way it's controlled now is by a sequence of static photos.
78
232008
3795
a način na koji se sada kontroliše je preko niza nepokretnih fotografija.
03:55
Notice how the wrinkles come and go, depending on the expression.
79
235827
3126
Obratite pažnju na to kako se bore pojavljuju i nestaju
u zavisnosti od izraza.
04:00
We can also use a video to drive the model.
80
240109
2746
Možemo da koristimo i snimak da upravljamo modelom.
04:02
(Video) Daniel Craig: Right, but somehow,
81
242879
2593
(Video) Danijel Krejg: Da, ali nekako smo uspeli
04:05
we've managed to attract some more amazing people.
82
245496
3771
da privučemo neke još neverovatnije ljude.
04:10
SS: And here's another fun demo.
83
250021
1642
SS: A evo još jednog zabavnog demo snimka.
04:11
So what you see here are controllable models
84
251687
2246
Ovde vidite upravljive modele ljudi,
04:13
of people I built from their internet photos.
85
253957
2444
koje sam napravio iz njihovih internet fotografija.
04:16
Now, if you transfer the motion from the input video,
86
256425
2904
Sada, ako se prebaci pokret sa ulaznog snimka
04:19
we can actually drive the entire party.
87
259353
2152
zapravo možemo da upravljamo celom družinom.
04:21
George W. Bush: It's a difficult bill to pass,
88
261529
2172
Džordž V. Buš: „Ovaj nacrt zakona će teško proći
04:23
because there's a lot of moving parts,
89
263725
2303
zato što ima mnogo pokretnih delova,
04:26
and the legislative processes can be ugly.
90
266052
5231
a proces zakonodavstva ume da bude gadan.“
04:31
(Applause)
91
271307
1630
(Aplauz)
04:32
SS: So coming back a little bit,
92
272961
1837
SS: Dakle, da se vratim malo unazad,
04:34
our ultimate goal, rather, is to capture their mannerisms
93
274822
3191
naš konačni cilj je radije da uhvatimo njihovu mimiku
04:38
or the unique way each of these people talks and smiles.
94
278037
3045
ili jedinstven način na koji svako od ovih ljudi priča ili se smeši.
04:41
So to do that, can we actually teach the computer
95
281106
2313
Da bismo to uradili, možemo li zaista naučiti računar
04:43
to imitate the way someone talks
96
283443
2222
da podražava način na koji neko govori
04:45
by only showing it video footage of the person?
97
285689
2420
pokazujući mu samo video snimke osobe?
04:48
And what I did exactly was, I let a computer watch
98
288898
2577
Tako sam pustio računaru da gleda
04:51
14 hours of pure Barack Obama giving addresses.
99
291499
3277
14 sati isključivo Baraka Obame i njegovih obraćanja.
04:55
And here's what we can produce given only his audio.
100
295443
3516
I evo šta možemo da izvedemo samo iz njegovog zvučnog snimka.
04:58
(Video) BO: The results are clear.
101
298983
1777
(Video) BO: Rezultati su jasni.
05:00
America's businesses have created 14.5 million new jobs
102
300784
4349
Američki biznisi su stvorili 14,5 miliona novih poslova
05:05
over 75 straight months.
103
305157
2774
tokom 75 meseci neprekidno.
05:07
SS: So what's being synthesized here is only the mouth region,
104
307955
2905
SS: Dakle, ono što se ovde spaja je samo oblast usta,
05:10
and here's how we do it.
105
310884
1540
i evo kako to radimo.
05:12
Our pipeline uses a neural network
106
312764
1826
Naš sistem koristi neuronsku mrežu
05:14
to convert and input audio into these mouth points.
107
314614
2936
da pretvori i dovede audio snimak u ove tačke usta.
05:18
(Video) BO: We get it through our job or through Medicare or Medicaid.
108
318547
4225
(Video) BO: Dobijamo to preko našeg posla ili preko zdravstvene zaštite.
05:22
SS: Then we synthesize the texture, enhance details and teeth,
109
322796
3420
SS: Tada stvaramo teksturu, poboljšavamo detalje i zube
05:26
and blend it into the head and background from a source video.
110
326240
3074
i stapamo u glavu i pozadinu iz izvornog snimka.
05:29
(Video) BO: Women can get free checkups,
111
329338
1905
(Video) BO: Žene mogu besplatno da se pregledaju
05:31
and you can't get charged more just for being a woman.
112
331267
2968
i ne može vam se naplatiti više samo zato što ste žena.
05:34
Young people can stay on a parent's plan until they turn 26.
113
334973
3306
Mladi mogu da ostanu u roditeljskom programu do 26. godine.
05:39
SS: I think these results seem very realistic and intriguing,
114
339267
2952
SS: Mislim da ovi rezultati izgledaju vrlo realistično i interesantno,
05:42
but at the same time frightening, even to me.
115
342243
3173
ali istovremeno zastrašujuće, čak i za mene.
05:45
Our goal was to build an accurate model of a person, not to misrepresent them.
116
345440
4015
Naš cilj je bio da napravimo precizan model osobe,
ne da je pogrešno predstavimo.
05:49
But one thing that concerns me is its potential for misuse.
117
349956
3111
Ali, ono što me brine je potencijal za zloupotrebu.
05:53
People have been thinking about this problem for a long time,
118
353958
2971
Ljudi su dugo razmišljali o ovom problemu,
05:56
since the days when Photoshop first hit the market.
119
356953
2381
još otkad je „Fotošop“ izašao na tržište.
05:59
As a researcher, I'm also working on countermeasure technology,
120
359862
3801
Kao istraživač, takođe radim na tehnologiji za protivmeru
06:03
and I'm part of an ongoing effort at AI Foundation,
121
363687
2942
i učestvujem u tekućem poduhvatu u fondaciji za veštačku inteligenciju
06:06
which uses a combination of machine learning and human moderators
122
366653
3397
gde se koristi kombinacija mašinskog učenja i ljudskih moderatora
06:10
to detect fake images and videos,
123
370074
2144
da se otkriju lažne slike i video-snimci,
06:12
fighting against my own work.
124
372242
1514
boreći se protiv sopstvenog posla.
06:14
And one of the tools we plan to release is called Reality Defender,
125
374675
3190
Jedan od alata koji planiramo da izdamo se zove „Branilac stvarnosti“ -
06:17
which is a web-browser plug-in that can flag potentially fake content
126
377889
4039
dodatak za internet pretraživače koji može da označi potencijalno lažne sadržaje
06:21
automatically, right in the browser.
127
381952
2533
automatski, direktno u samom pretraživaču.
06:24
(Applause)
128
384509
4228
(Aplauz)
06:28
Despite all this, though,
129
388761
1453
Uprkos svemu ovome,
06:30
fake videos could do a lot of damage,
130
390238
1840
lažni video-snimci mogu da učine dosta štete
06:32
even before anyone has a chance to verify,
131
392102
3294
čak i pre nego što iko stigne da ih proveri,
06:35
so it's very important that we make everyone aware
132
395420
2722
tako da je vrlo važno da svakoga osvestimo
06:38
of what's currently possible
133
398166
2007
o tome šta je trenutno moguće,
06:40
so we can have the right assumption and be critical about what we see.
134
400197
3369
tako da možemo pravilno da pretpostavimo i da posmatramo kritički.
06:44
There's still a long way to go before we can fully model individual people
135
404423
5007
I dalje smo daleko od toga da možemo potpuno da modelujemo pojedince
06:49
and before we can ensure the safety of this technology.
136
409454
2786
i pre nego što osiguramo bezbednost ove tehnologije.
06:53
But I'm excited and hopeful,
137
413097
1587
Ali ja sam uzbuđen i pun nade,
06:54
because if we use it right and carefully,
138
414708
3539
jer ako ga koristimo na pravi način i pažljivo,
06:58
this tool can allow any individual's positive impact on the world
139
418271
4309
ovaj alat može da omogući da pozitivni uticaj ma kog pojedinca na svet
07:02
to be massively scaled
140
422604
2190
bude mnogostruko uveličan
07:04
and really help shape our future the way we want it to be.
141
424818
2742
i zaista pomogne da oblikujemo budućnost u onakvu kakvu želimo.
07:07
Thank you.
142
427584
1151
Hvala vam.
07:08
(Applause)
143
428759
5090
(Aplauz)
About this website

This site will introduce you to YouTube videos that are useful for learning English. You will see English lessons taught by top-notch teachers from around the world. Double-click on the English subtitles displayed on each video page to play the video from there. The subtitles scroll in sync with the video playback. If you have any comments or requests, please contact us using this contact form.

https://forms.gle/WvT1wiN1qDtmnspy7