A Cognimetric Authentication Tool (CAT): Temporal Analysis of Touch Dynamics

Abstract

Much research in touch biometric authentication is grounded in a pragmatic, data-driven methodology, involving the collection and analysis of touch data to train machine learning models. In contrast, this research explores the integration of established theories of human cognition and interactive behaviour to inform the design of a Cognimetric Authentication Tool (CAT). In the field of cognitive science, time related measures are widely used to differentiate individuals during task performance. This investigation analyses two temporal measures of swipe and scroll interactions: touch durations (touch) and durations between touches (gap). An existing dataset, comprising interactions from 41 participants engaged in two realistic and cognitively demanding tasks—reading Wikipedia articles (read) and comparing image pairs (compare)—is utilised. The goal of this research is to develop methods for capturing, modelling and comparing participant behaviours for potential authentication applications. It adopts histograms to model and compare temporal behaviours based on the shapes of frequency distributions of each measure within each task. The metric Absolute Distribution Difference (ADD) is introduced by this research to quantify the consistency of temporal behaviour within participants and its distinctiveness across participants. The analysis reveals that intra-participant variations (inconsistency) are overshadowed by inter-participant differences (distinctiveness), which is necessary for authentication. However, the intricate relationship between them emphasises a trade-off; neither is independently sufficient for authentication. Trained only on genuine user’s behaviour, CAT drops error rates to around 10% for a single measure and halving to 5% when combining two measures. To accomplish this, CAT utilises 4 user profiles per participant, tailored to each measure and task, and consisting of the average behaviour of a participant and their personal inconsistency thresholds. This multi-level personalisation approach can compensate for the natural variability and context-dependent nature of human behaviour, and it extends to the fusion functions. Through the research, two sampling techniques are employed: initially, using the entire document as a sample, and subsequently, adopting action-based sampling (a conventional technique). In their current state, both sampling techniques are eligible for delayed authentication, as second factor authentication. Similarly, two fusion methods are employed: measures are combined within the same tasks (a conventional technique), and across tasks, providing complementing aspects of task-specific behaviours. Both sampling and fusion techniques prove effective particularly in relation to the previous research conducted with this dataset.