VIGIL: Verifying Identity via Gated Intermittent Likelihoods for Continuous Biometric Authentication
Cryptography and Security
Summary
The authors introduce VIGIL, a system designed to continuously check if a user is who they claim to be using multiple types of biometric data. Unlike older methods, VIGIL adjusts how it combines data from different sensors and uses a special model that carefully decides when more checks are needed. Their approach helps spot when an attacker is pretending to be someone else faster while still being easy for real users. Overall, the authors show that VIGIL improves security by making smarter decisions and reacting more quickly.
Authors
Aldridge Fonseca, Udayan Atreya, Amith Kamath Belman, Frank Sicong Chen
Abstract
Continuous multi-modal authentication has emerged as a necessity for securing modern environments against persistent threats. Existing temporal fusion techniques fail to identify a persistent attacker from a genuine user with poor signal strength. In this study, we propose VIGIL (Verifying Identity via Gated Intermittent Likelihoods for Continuous Biometric Authentication), a highly adaptive continuous authentication framework. We introduce configurable cross-modal fusion with per-modality weighting, enabling operators to select their choice of integration strategy. We improve temporal fusion using dual-state State Transition Machines (STM) with unidirectional transition matrices. A three-zone verification decision model that enables multi-round verification when evidence is inconclusive is used in combination with an adaptive shrinking verification window. Monotonic decay, backflow elimination and analytical evaluation demonstrate that the proposed framework effectively addresses the limitations of existing approaches and reduces the time to detect intrusions while maintaining high usability for legitimate users.