VIGIL: Verifying Identity via Gated Intermittent Likelihoods for Continuous Biometric Authentication

2026-07-18

AI Summary

This work addresses the challenge that existing continuous multimodal authentication methods struggle to distinguish persistent attacks from legitimate user anomalies caused by poor signal quality. To overcome this limitation, the paper proposes a highly adaptive continuous biometric authentication framework that innovatively integrates a configurable cross-modal weighting mechanism, a two-state state machine (STM) based on a unidirectional transition matrix, and a three-zone decision model supporting multi-round verification. The framework further incorporates an adaptive tightening of the verification window and a backflow elimination strategy. This approach significantly enhances detection sensitivity against sustained attacks while maintaining high system usability and effectively reducing intrusion response time.

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.

Problem

• continuous authentication
• multi-modal biometrics
• temporal fusion
• identity verification
• persistent attacker

Innovation

• continuous biometric authentication
• cross-modal fusion
• State Transition Machine
• adaptive verification window
• multi-modal authentication