Here at TypingDNA we present the various types of biometrics and explore their use for authentication and beyond. In this blog post, we will take a look at the signature analysis and cognitive biometrics.
Ever since the use of papyrus in ancient times, the way people type has been a fascinating topic. Graphology is the study of physical characteristics and patterns of handwriting. The first book on handwriting analysis appeared in 1575 and belonged to the renowned scholar, Juan Huarte de San Juan. To this day, the British Psychological Society ranks graphology alongside astrology, giving them both “zero validity”.
Nowadays, graphology has been replaced with signature analysis. This technology is made with specialized software and is currently used to analyze human signatures and evaluate shapes, contours, and movements used to create a personal trademark. Unlike graphology, the technology is not trying to find any information in the various shapes but rather compares samples to make sure it’s the same person. When forged, signatures are made more slowly, thus indicating potential fraud. A so-called motion-versus-time analysis is done to make sure signatures are genuine.
The use cases are varied, from banking, government, and insurance to health-care industries. In most of the cases, the signature analysis was intended to prevent identity theft but has been a modest solution to combat fraud.
There are multiple disadvantages to signature analysis such as if a person always has variations in their signature, so any electronic signature will differ from the previous one causing a chain of false positives or false negatives.
Given the latest innovation in biometric authentication variants, the signature analysis method can’t be regarded as a reliable anti-fraud solution.
Although more likely to belong to a Matrix movie script, an alternative method to the user authentication known as cognitive biometrics was introduced by Kenneth Revett of the British University in Egypt. The topic is largely discussed in the International Journal of Cognitive Biometrics (link). This method is based on acquiring information from users by collecting one or more biosignals through presenting users with one or more external stimuli, such as images. There are various techniques to obtain responses such as electroencephalogram (EEG), electrocardiogram (ECG), electrodermal response (EDR), and blood pulse volume (BVP).
Gaze interaction is situated somewhere between cognitive and behavioral biometrics. In the past few years, eye trackers or pupillometry have gained popularity among non-conventional authentication methods — the latest innovation in the field show and advancement in analyzing eye movements based on computer interaction. Among the advantages of gaze interaction, we list user-friendliness and reliability due to its near impossible way to mimic physiological and psychological responses.
Still, this method cannot yet be trusted for stand-alone usage, so in most cases, it is combined with other biometrics such as keystroke dynamics and mouse use analysis.