Original story at: Boston Globe Online
David Sadler For Congress 12th CD/Illinois

At MIT, they can put words in our mouths
By Gareth Cook, Globe Staff
Boston Globe Online

----- TEST BEGIN-----

Can you tell the difference between the real video clips and the synthetic ones created by new MIT software? Watch these clips, decide which are real and which are fake, then see the answers at the bottom of this article.

These clips require RealOne Player. Click here to download the player for free.

On Windows machines, clicking on each file link may give you the File Download dialog. You may:
Open this file from its current location, or
Save this file to disk

  |   Clip 1   |   Clip 2   |   Source: Massachusetts Institute of Technology.

----- TEST END-----

CAMBRIDGE - Scientists at the Massachusetts Institute of Technology have created the first realistic videos of people saying things they never said - a scientific leap that raises unsettling questions about falsifying the moving image.

In one demonstration, the researchers taped a woman speaking into a camera, and then reprocessed the footage into a new video that showed her speaking entirely new sentences, and even mouthing words to a song in Japanese, a language she does not speak. The results were enough to fool viewers consistently, the researchers report.

The technique's inventors say it could be used in video games and movie special effects, perhaps reanimating Marilyn Monroe or other dead film stars with new lines. It could also improve dubbed movies, a lucrative global industry.

But scientists warn the technology will also provide a powerful new tool for fraud and propaganda - and will eventually cast doubt on everything from video surveillance to presidential addresses.

" This is really groundbreaking work, " said Demetri Terzopoulos, a leading specialist in facial animation who is a professor of computer science and mathematics at New York University. But " we are on a collision course with ethics. If you can make people say things they didn't say, then potentially all hell breaks loose. "

The researchers have already begun testing the technology on video of Ted Koppel, anchor of ABC's " Nightline, " with the aim of dubbing a show in Spanish, according to Tony F. Ezzat, the graduate student who heads the MIT team. Yet as this and similar technology makes its way out of academic laboratories, even the scientists involved see ways it could be misused: to discredit political dissidents on television, to embarrass people with fabricated video posted on the Web, or to illegally use trusted figures to endorse products.

" There is a certain point at which you raise the level of distrust to where it is hard to communicate through the medium, " said Kathleen Hall Jamieson, dean of the Annenberg School for Communication at the University of Pennsylvania. " There are people who still believe the moon landing was staged. "

Currently, the MIT method is limited: It works only on video of a person facing a camera and not moving much, like a newscaster. The technique only generates new video, not new audio.

But it should not be difficult to extend the discovery to work on a moving head at any angle, according to Tomaso Poggio, a neuroscientist at the McGovern Institute for Brain Research, who is on the MIT team and runs the lab where the work is being done. And while state-of-the-art audio simulations are not as convincing as the MIT software, that barrier is likely to fall soon, researchers say.

" It is only a matter of time before somebody can get enough good video of your face to have it do what they like, " said Matthew Brand, a research scientist at MERL, a Cambridge-based laboratory for Mitsubishi Electric.

For years, animators have used computer technology to put words in people's mouths, as they do with the talking baby in CBS's " Baby Bob " - creating effects believable enough for entertainment, but still noticeably computer-generated. The MIT technology is the first that is " video-realistic, " the researchers say, meaning volunteers in a laboratory test could not distinguish between real and synthesized clips. And while current computer-animation techniques require an artist to smooth out trouble spots by hand, the MIT method is almost entirely automated.

Previous work has focused on creating a virtual model of a person's mouth, then using a computer to render digital images of it as it moves. But the new software relies on an ingenious application of artificial intelligence to teach a machine what a person looks like when talking.

Starting with between two and four minutes of video - the minimum needed for the effect to work - the computer captures images which represent the full range of motion of the mouth and surrounding areas, Ezzat said.

The computer is able to express any face as a combination of these faces (46 in one example), the same way that any color can be represented by a combination of red, green, and blue. The computer then goes through the video, learning how a person expresses every sound, and how it moves from one to the next.

Given a new sound, the computer can then generate an accurate picture of the mouth area and virtually superimpose it on the person's face, according to a paper describing the work. The researchers are scheduled to present the paper in July at Siggraph, the world's top computer graphics conference.

The effect is significantly more convincing than a previous effort, called Video Rewrite, which recorded a huge number of small snippets of video and then recombined them. Still, the new method only seems lifelike for a sentence or two at a time, because over longer stretches, the speaker seems to lack emotion.

MIT's Ezzat said that he would like to develop a more complex model that would teach the computer to simulate basic emotions.

A specialist can still detect the video forgeries, but as the technology improves, scientists predict that video authentication will become a growing field - in the courts and elsewhere - just like the authentication of photographs. As video, too, becomes malleable, a society increasingly reliant on live satellite feeds and fiber optics will have to find even more direct ways to communicate.

" We will probably have to revert to a method common in the Middle Ages, which is eyewitness testimony, " said the University of Pennsylvania's Jamieson. " And there is probably something healthy in that. "

Gareth Cook can be reached at cook@globe.com.


Answers: Clip 1 is real; clip 2 is synthetic.

This story ran on page A1 of the Boston Globe on 5/15/2002.
© Copyright 2002 Globe Newspaper Company.

Added: 2004.11.18

Steve Mcqueen Ford Mustang commercial 2004.11
Photo: Ford Motor Company & prweb.com

Ford Brings Actor Steve McQueen Back To Life In Mustang Ads
Detroit Free Press
Motor Trend
October 15, 2003

To introduce its six new cars and trucks, Ford Motor Co.'s namesake brand is launching an aggressive and energetic marketing campaign.

Highlighted by the digital resurrection of the late movie legend Steve McQueen, the ads also feature a new tagline and a hip Jimi Hendrix-like rendition of the national anthem that uses the sounds of a Mustang's engine and wheels.

Ford Division President Steve Lyons unveiled the ads and discussed the division's marketing strategy during an announcement Thursday at Dearborn's Ford Community and Performing Arts Center. About 1,000 company employees attended.


Two separate "The Legend Lives" Mustang commercials -- one featuring McQueen and the other a clever interpretation of the national anthem -- are to begin airing in November.

In "Cornfield," McQueen is beckoned to a field in a way reminiscent of the 1989 Kevin Costner movie, "Field of Dreams." A farmer builds a racetrack, and McQueen materializes like a ghost to rip it up in a shiny new Mustang, just as he did in the 1968 film "Bullitt."

A red Mustang proves the centerpiece during "Anthem," 60 seconds of a V8 engine humming and rumbling, and wheels spinning and screeching, to sound like "The Star Spangled Banner."

Added: 2006.01.22

When Seeing and Hearing Isn't Believing
Washington Post

"For Hollywood, it is special effects. For covert operators in the U.S. military and intelligence agencies, it is a weapon of the future.

Digital morphing — voice, video, and photo — has come of age, available for use in psychological operations. PSYOPS, as the military calls it, seek to exploit human vulnerabilities in enemy governments, militaries and populations to pursue national and battlefield objectives.

Pentagon planners started to discuss digital morphing after Iraq's invasion of Kuwait in 1990. Covert operators kicked around the idea of creating a computer-faked videotape of Saddam Hussein crying or showing other such manly weaknesses, or in some sexually compromising situation. The nascent plan was for the tapes to be flooded into Iraq and the Arab world.

The tape war never proceeded, killed, participants say, by bureaucratic fights over jurisdiction, skepticism over the technology, and concerns raised by Arab coalition partners.

But the "strategic" PSYOPS scheming didn't die. What if the U.S. projected a holographic image of Allah floating over Baghdad urging the Iraqi people and Army to rise up against Saddam, a senior Air Force officer asked in 1990? According to a military physicist given the task of looking into the hologram idea, the feasibility had been established of projecting large, three-dimensional objects that appeared to float in the air.

The Gulf War hologram story might be dismissed were it not the case that washingtonpost.com has learned that a super secret program was established in 1994 to pursue the very technology for PSYOPS application. The "Holographic Projector" is described in a classified Air Force document as a system to "project information power from space ... for special operations deception missions."

Voice-morphing? Fake video? Holographic projection? They sound more like Mission Impossible and Star Trek gimmicks than weapons. Yet for each, there are corresponding and growing research efforts as the technologies improve and offensive information warfare expands.

Video and photo manipulation has already raised profound questions of authenticity for the journalistic world. With audio joining the mix, it is not only journalists but also privacy advocates and the conspiracy-minded who will no doubt ponder the worrisome mischief that lurks in the not too distant future."

Added: 2006.01.22

5.6 Airborne Holographic Projector
Washington Post
Extract from Air Force 2025
Original link: USAF
Why this link is no longer there.
Wayback Machine archive
FAS archive of Air Force 2025

"The holographic projector displays a three-dimensional visual image in a desired location, removed from the display generator. The projector can be used for psychological operations and strategic perception management. It is also useful for optical deception and cloaking, providing a momentary distraction when engaging an unsophisticated adversary."

Added: 2018.02.19

Fake videos are on the rise. As they become more realistic, seeing shouldn't always be believing
Los Angeles Times

Original link: LA Times
Wayback Machine archive if needed.

"All it takes is a single selfie.

"From that static image, an algorithm can quickly create a moving, lifelike avatar: a video not recorded, but fabricated from whole cloth by software.

"With more time, Pinscreen, the Los Angeles start-up behind the technology, believes its renderings will become so accurate they will defy reality.

"You won't be able to tell," said Hao Li, a leading researcher on computer-generated video at USC who founded Pinscreen in 2015. "With further deep-learning advancements, especially on mobile devices, we'll be able to produce completely photoreal avatars in real time."
  • YouTube: Pinscreen Photoreal 3D Facial Retargeting from a Single Image (LA Times)

    Added: 2018.02.19

    Adobe's VoCo voice project: Now you really can put words in someone else's mouth
    It may be hard to trust the authenticity of any recorded speech in the not too distant future.
    ZD Net

    Original link: Project VoCo at its annual MAX event
    Wayback Machine archive if needed.

    "You may soon be able to make people say things they never did, if Adobe one day gets to release its new voice-editing software.

    "The company showed off Project VoCo yesterday at its annual MAX event, revealing a tool that will do for audio what Photoshop does for the manipulation of images.

    "As The Verge reports, with about a 20-minute recording of a speaker's voice, VoCo can be used to insert single new words that the speaker never said and even create entirely new, natural-sounding sentences.

    "The technology was demonstrated by researcher Zeyu Jin, who was offering MAX attendees a sneak peak at products under development. It's not clear whether VoCo will eventually be released as a product. Adobe Research is collaborating with Princeton University on the project."
  • YouTube: VoCo Demo at Adobe Max 2016

    Added: 2006.01.22: controlled media

    Army 'psyops' at CNN
    by Geoff Metcalf [gmetcalf@worldnetdaily.com]

    CNN employed active duty U.S. Army psychological operations personnel last year, WorldNetDaily has confirmed through several sources at Fort Bragg and elsewhere.

    Maj. Thomas Collins, U.S. Information Service has confirmed that "psyops" (psychological operations) personnel, soldiers and officers, have worked in the CNN headquarters in Atlanta. The lend/lease exercise was part of an Army program called "Training With Industry." According to Collins, the soldiers and officers, "... worked as regular employees of CNN. Conceivably, they would have worked on stories during the Kosovo war. They helped in the production of news."

    When asked if the introduction of military personnel into a civilian news organization was standard operating procedure, one source said, "That question is above my pay grade ... but I hope so. It's what we do."

    The CNN military personnel were members of the Airmobile Fourth Psychological Operations Group, stationed at Fort Bragg, North Carolina. One of the main tasks of this group of almost 1200 soldiers and officers is to spread 'selected information.' Critics say that means dissemination of propaganda.

    Cable News Network suffered a major embarrassment in the wake of the 'Tailwind' story it aired, alleging the U.S. government used lethal sarin gas to kill suspected defectors during the Vietnam war. After WorldNetDaily was the first news organization to expose the fraudulent news production, two CNN producers were fired and, eventually, CNN veteran reporter Peter Arnett also was ousted. In that case, Retired Air Force Maj. Gen. Perry Smith quit his long-time job as a military adviser to CNN.

    What about now? Has the U.S. military been in a position to have influenced directly CNN's news reports about the crisis in Kosovo?

    Collins claims a "handful" of military assets were assigned to CNN for weeks "to get to know the company and to broaden their horizons." The Major asserts "they didn't work under the control of the army."

    Several sources have confirmed the temporary outplacement of U.S. Army psyops personnel started two or three years ago, and they have been integrated into "various sectors of society." The assignment durations have been short-term up to one full year, depending on the mission. When asked, "What were the missions?" responses to WND varied from "No comment.", "... need to know," to smiles, and, in one case, an obscene recommendation.

    CNN is the most watched and widely viewed news outlet in the world. During Operation Desert Storm, Saddam Hussein regularly watched CNN for battlefield intelligence. The symbiotic, intimate relationship between CNN and army psyops specialists has raised many eyebrows, with critics saying it raises doubts about CNN's journalistic integrity and independence.

    The Fourth Psyop Group has been involved in the Gulf War, the Bosnian War and the Kosovo crisis. American psyops troops attempt to influence media and public opinion in armed conflicts in which American state interests are said to be at stake.

    News coverage of the war in Kosovo, by CNN and other media, has been criticized as "one-sided, overly emotional, over-simplified and relying too heavily on NATO officials," observed a report from the Netherlands.

    CNN has not thus far commented officially on the allegations. Megan Mahoney, a CNN spokeswoman recently said, "I don't believe that we would employ military personnel; it doesn't seem like something we would normally do." However, now that the U.S. Army Information Service has confirmed the news, Mahoney said she would have to contact CNN's senior officials.