SSPRA: A Robust Approach to Continuous Authentication Amidst Real-World Adversarial Challenges

In real-world deployment, continuous authentication for mobile devices faces challenges such as intermittent data streams, variable data quality, and varying modality reliability. To address these challenges, we introduce a framework based on Markov process, named State-Space Perturbation-Resistant Approach (SSPRA). SSPRA integrates a two-level multi-modality fusion mechanism and dual state transition machines (STMs). This two-level fusion integrates probabilities from available modalities at each inspection (vertical-level) and evolves state probabilities over time (horizontal-level), thereby enhancing decision accuracy. It effectively manages modality disruptions and adjusts to variations in modality reliability. The dual STMs trigger appropriate responses upon detecting suspicious data, managing data fluctuations and extending operational duration, thus improving user experience. In our simulations, covering standard operations and adversarial scenarios like zero to non-zero-effort (ZE/NZE) attacks, modality disconnections, and data fluctuations, SSPRA consistently outperformed all baselines, including Sim's HMM and three state-of-the-art deep-learning models. Notably, in adversarial attack scenarios, SSPRA achieved substantial reductions in False Alarm Rate (FAR) - 36.31%, 36.58%, and 8.26% - and improvements in True Alarm Rate (TAR) - 33.15%, 33.75%, and 5.1% compared to the DeepSense, Siamese-structured network, and UMSNet models, respectively. Furthermore, it outperformed all baselines in modality disconnection and fluctuation scenarios, underscoring SSPRA's potential in addressing real-world challenges in mobile device authentication.