Technology would help detect terrorists before they strike

Oct 05, 2007

Are you a terrorist? Airport screeners, customs agents, police officers and members of the military who silently pose that question to people every day, may soon have much more than intuition to depend on to determine the answer.

Computer and behavioral scientists at the University at Buffalo are developing automated systems that track faces, voices, bodies and other biometrics against scientifically tested behavioral indicators to provide a numerical score of the likelihood that an individual may be about to commit a terrorist act.

“The goal is to identify the perpetrator in a security setting before he or she has the chance to carry out the attack,” said Venu Govindaraju, Ph.D., professor of computer science and engineering in the UB School of Engineering and Applied Sciences. Govindaraju is co-principal investigator on the project with Mark G. Frank, Ph.D., associate professor of communication in the UB College of Arts and Sciences.

The project, recently awarded an $800,000 grant by the National Science Foundation, will focus on developing in real-time an accurate baseline of indicators specific to an individual during extensive interrogations while also providing real-time clues during faster, routine security screenings.

“We are developing a prototype that examines a video in a number of different security settings, automatically producing a single, integrated score of malfeasance likelihood,” he said.

A key advantage of the UB system is that it will incorporate machine learning capabilities, which will allow it to “learn” from its subjects during the course of a 20-minute interview.

That’s critical, Govindaraju said, because behavioral science research has repeatedly demonstrated that many behavioral clues to deceit are person-specific.

“As soon as a new person comes in for an interrogation, our program will start tracking his or her behaviors, and start computing a baseline for that individual ‘on the fly’,” he said.

The researchers caution that no technology, no matter how precise, is a substitute for human judgment.

“No behavior always guarantees that someone is lying, but behaviors do predict emotions or thinking and that can help the security officer decide who to watch more carefully,” said Frank.

He noted that individuals often are randomly screened at security checkpoints in airports or at border crossings.

“Random screening is fair, but is it effective?” asked Frank. “The question is, what do you base your decision on -- a random selection, your gut reaction or science? We believe science is a better basis and we hope our system will provide that edge to security personnel.”

Govindaraju added that the UB system also would avoid some of the pitfalls that hamper a human screener’s effectiveness.

“Human screeners have fatigue and bias, but the machine does not blink,” he said.

The UB project is designed to solve one of the more challenging problems in developing accurate security systems -- fusing information from several biometrics, such as faces, voices and bodies.

“No single biometric is suited for all applications,” said Govindaraju, who also is founder and director of UB’s Center for Unified Biometrics and Sensors. “Here at CUBS, we take a unique approach to developing technologies that combine and ‘tune’ different biometrics to fit specific needs. In this project, we are focusing on how to analyze different behaviors and come up with a single malfeasance indicator.”

The UB project is among the first to involve computer scientists and behavioral scientists working together to develop more accurate detection systems based on research from each field.

Both researchers have spent their careers studying complementary areas. Since completing his doctoral dissertation on using computational tools to do facial recognition, Govindaraju has focused on problems in pattern recognition and artificial intelligence. Since founding CUBS in 2003, he has worked on a broad range of biometric technologies and devices.

Frank, a social psychologist, has spent his career conducting research on human nonverbal communication that strongly suggests whether or not an individual is feeling emotions or telling the truth. He founded the Communication Science Center at UB in 2005 and his work, recognized and utilized by security officials around the world, now provides important information for UB computer scientists.

Frank and Govindaraju began working together partly as a result of UB 2020, the university’s strategic plan, which emphasizes strengthening interdisciplinary research.

“What I like about working with Venu and his team at CUBS is that they are creating new algorithms that hold the exciting possibility of revealing information and patterns that will help us spot potential bad guys,” said Frank. “We expect that there will be an advantage to combining the behavioral understanding of people with algorithm development to make better predictions.”

They expect to have a working prototype of the full system within a few years.

Source: University at Buffalo

Explore further: Artificial intelligence identifies the musical progression of the Beatles

add to favorites email to friend print save as pdf

Related Stories

Image: Chandra's view of the Tycho Supernova remnant

18 minutes ago

More than four centuries after Danish astronomer Tycho Brahe first observed the supernova that bears his name, the supernova remnant it created is now a bright source of X-rays. The supersonic expansion of ...

Monkeys fear big cats less, eat more, with humans around

1 hour ago

Some Monkeys in South Africa have been found to regard field scientists as human shields against predators and why not if the alternative is death by leopard? The researchers found the monkeys felt far safer ...

Recommended for you

Designing exascale computers

Jul 23, 2014

"Imagine a heart surgeon operating to repair a blocked coronary artery. Someday soon, the surgeon might run a detailed computer simulation of blood flowing through the patient's arteries, showing how millions ...

User comments : 1

Adjust slider to filter visible comments by rank

Display comments: newest first

HarryStottle
5 / 5 (1) Oct 15, 2007
Approaches like this are almost always doomed to fail because, ultimately, they rely on a statistical approach and try to answer the question (in this case): "What is the probability that this subject is concealing malicious intent?"

Let's imagine they can eventually achieve 99% accuracy. This implies a false negative rate of 1% which we can live with. But a false positive rate, also of 1%, is utterly unacceptable. It implies thousands of passengers a day being pulled out of the queues for hostile interrogation, probably causing them to miss their flights or the flights to be delayed. The level of disruption and hostility makes measures like this untenable.

Only when you have 100% accurate brainscanners capable of 100% accurate lie detection will we have a technological filter for malice. And if we ever get to that stage, the first people we will need to apply it to will be the politicians and police before we let it loose on the people...