Fake videos of real people -- and how to spot them

Look at these images.

Now, tell me which Obama here is real.

(Video) Barack Obama: To help families
refinance their homes,

to invest in things
like high-tech manufacturing,

clean energy,

and the infrastructure
that creates good new jobs.

Supasorn Suwajanakorn: Anyone?

The answer is none of them.

(Laughter)

None of these is actually real.

So let me tell you how we got here.

My inspiration for this work
was a project meant to preserve

our last chance for learning
about the Holocaust from the survivors.

It's called New Dimensions in Testimony,

and it allows you to have
interactive conversations

with a hologram
of a real Holocaust survivor.

(Video) Question: How did you
survive the Holocaust?

(Video) Answer: How did I survive?

I survived,

I believe,

because providence watched over me.

SS: Turns out these answers
were pre-recorded in a studio.

Yet the effect is astounding.

You feel so connected to his story
and to him as a person.

I think there is something special
about human interaction

that makes it much more profound

and personal

than what books or lectures
or movies could ever teach us.

So I saw this and began to wonder,

can we create a model
like this for anyone?

A model that looks, talks,
and acts just like them?

So I set out to see if this could be done,

and eventually came up
with a new solution

that can build a model of a person

using nothing but these:

existing photos and videos of a person.

If you can leverage this kind
of passive information,

just photos and video that are out there,

that's the key to scaling to anyone.

By the way, here's Richard Feynman,

who in addition to being
a Nobel Prize Winner in physics

was also known as a legendary teacher.

Wouldn't it be great
if we could bring him back

to give his lectures
and inspire millions of kids,

perhaps not just in English
but in any language?

Or if you could ask our grandparents
for advice and hear those comforting words

even if they are no longer with us?

Or maybe using this tool,
books authors, alive or not,

could read aloud all of their books
for anyone interested.

The creative possibilities
here are endless,

and to me that's very exciting.

And here's how it's working so far.

First, we introduce a new technique

that can reconstruct
a high-detailed 3D face model

from any image

without ever 3D-scanning the person.

And here's the same output model
from different views.

This also works on videos

by running the same algorithm
on each video frame

and generating a moving 3D model.

And here's the same
output model from different angles.

It turns out, this problem
is very challenging,

but the key trick is that we are going
to analyze a large photo collection

of the person beforehand.

For George W. Bush,
we can just search on Google,

and from that, we are able
to build an average model,

an iterative, refined model
to recover the expression

in fine details like creases and wrinkles.

What's fascinating about this
is that the photo collection

can come from your typical photos.

It doesn't really matter
what expression you're making

or where you took those photos.

What matters is that
there are a lot of them.

And we are still missing color here,

so next we develop
a new blending technique

that improves upon
a single averaging method

and produces sharp
facial textures and colors.

And this can be done for any expression.

Now we have a control
of a model of a person,

and the way it's controlled now
is by a sequence of static photos.

Notice how the wrinkles come and go
depending on the expression.

We can also use a video
to drive the model.

(Video) Daniel Craig: Rory, but somehow
we've managed to attract

more amazing people.

SS: And here's another fun demo.

So what you see here
are controllable models

of people I built
from their internet photos.

Now, if you transfer the motion
from the input video,

we can actually drive the entire party.

(Video) George W. Bush:
It's a very difficult bill to pass,

because there's a lot of moving parts,

and the legislative process can be ugly.

(Applause)

SS: So coming back a little bit,

our ultimate goal, rather,
is to capture their mannerisms

or the unique way each
of these people talks and smiles.

So to do that, can we
actually teach the computer

to imitate the way someone talks

by only showing it
video footage of the person?

And what I did exactly was,
I let a computer watch

14 hours of pure Barack Obama
giving addresses.

And here's what we can produce
given only his audio.

(Video) BO: The results are clear.

America's business have created
14.5 million new jobs

over 75 straight months.

SS: So what's being synthesized here
is only the mouth region,

and here's how we do it.

Our pipeline uses a neural network

to convert and input audio
into these mouth points.

(Video) BO: We get it through our job
or through Medicare or Medicaid.

SS: Then we synthesize the texture,
enhance details and teeth,

and blend it into the head
and background from a source video.

(Video) BO: Women can get free checkups,

and you can't get charged more
just for being a woman.

Young people can stay
on a parent's plan until they turn 26.

SS: I think these results
seem very realistic and intriguing,

but at the same time frightening,

even to me.

Our goal was to build an accurate model
of a person, not to misrepresent them.

But one thing that concerns me
is its potential for misuse.

People have been thinking
about this problem for a long time,

since the days when Photoshop
first hit the market.

As a researcher, I'm also working
on countermeasure technology,

and I'm part of an ongoing
effort at AI Foundation

which uses a combination
of machine learning and human moderators

to detect fake images and videos,

fighting against my own work.

And one of the tools we plan to release
is called Reality Defender,

which is a web browser plugin
that can flag potentially fake content

automatically right in the browser.

(Applause)

Despite all this, though,

fake videos could do a lot of damage,

even before anyone has a chance to verify,

so it's very important
that we make everyone aware

of what's currently possible

so we can have the right assumption
and be critical about what we see.

There's still a long way to go before
we can fully model individual people

and before we can ensure
the safety of this technology,

but I'm excited and hopeful

because if we use it right and carefully,

this tool can allow any individual's
positive impact on the world

to be massively scaled

and really help shape our future
the way we want it to be.

Thank you.

(Applause)