PresSafe: Barometer-Based On-Screen Pressure-Assisted Implicit Authentication for Smartphones

Abstract

Graphic-pattern-based implicit authentication has been successfully exploited to elevate the security of smartphones. On-screen pressure is one of the key features in such approach since it can reveal users' touch pattern. However, state-of-the-art approaches rely on a system API to obtain on-screen pressure, which is not adequately accurate and cannot meet the demands of robust implicit authentication. To bridge this gap, we propose PresSafe, a novel implicit authentication system that utilizes the smartphone's built-in barometer sensor to measure pressure during the unlocking process, and to utilize the pressure data in authentication. A key technical challenge in utilizing barometer sensing, however, is to understand the user activity through measured pressure. To overcome this challenge, PresSafe leverages barometer data along with data from other conventional but heterogeneous ambient sensors to produce accurate and robust user activity descriptions. PresSafe utilizes a transfer learning based hybrid workflow to integrate user activity representation learning with a lightweight classical authentication algorithm to obtain a unified model. This approach offloads computational cost from the terminal and addresses privacy concerns. To ensure applicability of our approach despite data heterogeneity and insufficient training data, we utilize a channel-adaptive data processing mechanism. Extensive experiments utilizing more than 70,000 records from 23 volunteers in 6 different locations show that PresSafe achieves an FAR of 0.45 %, an FRR of 0.49 %, and an EER of 0.47 %, which clearly demonstrate its superiority over several existing solutions.

Pattern unlocking guided multi‐modal continuous authentication for smartphone with multi‐branch context‐aware representation learning and auto encoder

“…Proposed by Google, 30 pattern unlocking is now popular among smartphone users. We choose four typical patterns (Figure 8), as following the setting in References 14 and 15. For a $$$ 3\times 3 $$$ dot grid, an unlock pattern needs to involve at least 4 dots, but no more than 9 dots in total. Any dot in the grid can only be used once. Skipping any unconnected dots on the route of a pattern is not allowed, any used dots covered by the path will be automatically joined. Skipping an already used dot and connect to an unused dot in its neighborhood is possible. …”

“…We also choose another two state-of-the-art smartphone continuous authentication works that do not explicitly discuss the utilization of contextual information 13,15 to compare the efficiency of the authentication framework. To conduct this comparison, we use the dataset collected in a fully static condition.…”

“…We use four unlocking patterns (Figure 8) that are widely used in existing works. 14,15 Despite the overall performance provided in Section 6.2, we compare the differences in performance of these four unlocking patterns. The results are shown in Table 8.…”

“…This meticulous approach enables a more granular analysis of the data and, consequently, an improvement in the precision of their model. In a noteworthy development, Yao et al 15 have taken into account the pressure applied to the screen during user interactions. They have introduced additional features on the third dimension of the screen, a novel approach that has proven to augment the overall performance of their system.…”

“…Challenge 1: Recognition of various contexts and application scenes. Existing works 12,14,15 point out that a comprehensive user profile generated from a wider sensor set, especially those contains conventional user behaviors and contextual information, is essential for a robust authentication system (Figure 1A). Existing works 9,10,[12][13][14]16 usually involve a two-stage approach in implementation, which means the optimization of the feature extraction backbone and the authentication module is weakly related.…”