“CIA Faces Up to a Better Lie Detector”

John Geralds reports for vnunet.com. Excerpt:

Two US research teams developing software that can recognise and analyse facial expressions have caught the attention of the US Central Intelligence Agency (CIA), as a potential tool to build a better lie detector.

Professor Terry Sejnowski, who leads one of the research teams in the Computational Neurobiology Laboratory at the Salk Institute for Biological Studies in California, calls the new facial technology an “emotion detector”.

“It could be used in conjunction with a polygraph or more casually, for example, a camera hidden in the corner of a room. It distinguishes finer gradations of emotional response – whether the person is truly happy, sad or angry.”

Professor Sejnowski’s work coincides with that of Professor Jeffrey Cohn of the University of Pittsburgh and Carnegie Mellon University.

Cohn’s work is based on the coding system known as the Facial Action Coding System (FACS) developed in the 1970s. It defines the movements of each of the 44 muscles in the human face, information used by experts to study frames of video images and “read” people’s expressions.

“Our Automated Face Analysis system studies wrinkles and furrows, as well as other features, to quantify subtle changes in facial motion, rather than focusing on prototypic expressions,” explains Professor Cohn.

“Scientists Eyeing High-Tech Upgrade for Lie Detectors”

Boston Globe staff writer Patricia Wen reports. Excerpt:

Former CIA agent Aldrich Ames easily fooled lie detector tests, concealing his work as a Russian spy. But could he have duped a ”brain fingerprinting” exam, which probes what people know by checking their electrical brain waves?

Iowa-based neuroscientist Lawrence Farwell…is eager to see his ”brain fingerprinting” work get into more courtrooms, convinced as he is that it has a near-perfect accuracy rate.

His method focuses on a specific electrical brain wave, called a P300, which activates when a person sees a familiar object. The subject wears a headband of electrodes and faces a computer screen, which flashes photos.

This technique provides a potential window into someone’s past visual experience. If a person looks at random pictures of weapons without activating a P300 wave, these objects are presumably unknown to him. But if the murder weapon is shown and a P300 wave activates, then the person clearly has some experience with that weapon.

”This technique is used to see if they have the information stored in their brain or not,” said Farwell, a Harvard graduate who now runs Brain Wave Science in Fairfield, Iowa. ”All of this relates indirectly to lie detection.”

Of course, for the P300 to be truly incriminating, the prosecutor would have to show that the tested person didn’t see that murder weapon in some other innocent way, such as in media accounts or by being a bystander.

His ”brain fingerprinting” helmet of electrodes is currently available within the CIA, Farwell said, though he doesn’t know if or how often it’s used. However, Farwell knows some strategies for using P300 to detect moles. A US agent suspected of being a spy for Cuba, for instance, could be shown objects known only to Cuban undercover agents, something as simple as a job-related paper form or the ”contact” person.

Farwell’s lie detection technique won a modest legal victory in March when an Iowa judge ruled there was enough scientific basis to admit ”brain fingerprinting” results as evidence in the case of Terry Harrington, a convicted murderer trying to win a new trial. Farwell showed that Harrington did not have a P300 wave when shown key parts of the crime scene, but did emit the P300 wave when shown scenes from his alibi, suggesting he was unfamiliar with the crime.

The judge did not grant a new trial and Harrington is appealing.