The faces and behaviour of online avatars could help identify the people controlling them, scientists believe.
Using both characteristics, researchers hope to develop techniques for checking whether the digital characters are who they claim to be.
Such information could be used in situations where login details are not visible or for law enforcement.
Impersonation of avatars is expected to become a growing problem as real life and cyberspace increasingly merge.
Avatars are typically used to represent players in online games such as World of Warcraft and in virtual communities like Second Life.
As their numbers grow, it will become important to find ways to identify those we meet regularly, according to Dr Roman Yampolskiy from the University of Louisville.
Working out if their controller is male or female has an obvious commercial benefit, he said. But discovering that the same person controlled different avatars in separate spaces would be even more useful.
"It's useful for profiling of avatars for marketing purposes by businesses in virtual worlds," explained Dr Yampolskiy.
"It also has some applications in forensic tracking of avatars across multiple virtual communities."
The technology may also have implications for security if a game account is hacked and stolen.
Behavioural analysis could help prove whether an avatar is under the control of its usual owner by watching to see if it acts out of character.
The research looked at monitoring for signature gestures, movements and other distinguishing characteristics.
Researchers discovered that the lack of possible variations on a avatar's digital face, when compared to a real human, made identification tricky.
However, those limited options are relatively simple to measure, because of the straightforward geometries involved in computer-generated images.
Dr Yampolskiy's team generated large data sets made up of many possible faces in Second Life and Entropia Universe and then studied them to spot key characteristics.
"It's very preliminary work as we are still collecting data," he said. "So far we have been very successful."
Dr Yampolskiy pointed out that another factor driving the need for avatar identification was the increasing use of telepresence and augmented reality.
Especially for businesses, it will be important to ensure that on-screen facsimiles represent the people they purport to.
Further work by the group will extend the identifying work and behaviour monitoring to robots.
As more and more machines start to work alongside people access to controlled areas would rely on being able to tell one from another.