BioTouchPass2: Touchscreen Password Biometrics Using Time-Aligned Recurrent Neural Networks

Abstract

Passwords are still used on a daily basis for all kind of applications. However, they are not secure enough by themselves in many cases. This work enhances password scenarios through two-factor authentication asking the users to draw each character of the password instead of typing them as usual. The main contributions of this study are as follows: i) We present the novel MobileTouchDB public database, acquired in an unsupervised mobile scenario with no restrictions in terms of position, posture, and devices. This database contains more than 64K on-line character samples performed by 217 users, with 94 different smartphone models, and up to 6 acquisition sessions. ii) We perform a complete analysis of the proposed approach considering both traditional authentication systems such as Dynamic Time Warping (DTW) and novel approaches based on Recurrent Neural Networks (RNNs). In addition, we present a novel approach named Time-Aligned Recurrent Neural Networks (TA-RNNs) 1 . This approach combines the potential of DTW and RNNs to train more robust systems against attacks.A complete analysis of the proposed approach is carried out using both MobileTouchDB 2 and e-BioDigitDB 3 databases. Our proposed TA-RNN system outperforms the state of the art, achieving a final 2.38% Equal Error Rate, using just a 4digit password and one training sample per character. These results encourage the deployment of our proposed approach in comparison with traditional typed-based password systems where the attack would have 100% success rate under the same impostor scenario.

Handwriting Biometrics: Applications and Future Trends in e-Security and e-Health

“…More recently, in [20] writer verification rates of 96.2% were achieved for handwritten passwords consisting of 7 digits written with the fingertip over the touchscreen of COTS smartphones and 94.1% for 4-digit passwords. In a subsequent study, the same authors were able to obtain similar authentication accuracy for more challenging and realistic acquisition conditions (in the wild including cross-device comparisons over a diverse pool of COST smartphones consisting of 94 different models) by considering characters and symbols instead of only numerical digits to construct the passwords [36].…”

“…As a summary of the research discussed in the present paper, on the one hand, the state of the art in applications based on online handwritten tasks can be considered: a) Mature in security applications based on signature [4,18] b) Incipient in security applications based on the handwritten text [20,36] c) Incipient in security applications based on drawing tasks [37,38] d) Incipient in health applications based on handwriting text and drawing tasks [3,47,[100][101][102]] e) Incipient in health applications based on signature [3,18,47,99] On the other hand, it is difficult to find published research in joint applications where security is studied in combination with one of the following health-related aspects: f) Is the user to authenticate under stress? g) Is he suffering any disease that makes him unable to understand the real implication on his acts?…”

“…Development and scientific progress in biometric security applications based on handwritten text (capital letters, cursive letters, etc.) [20,36], where the goal is not the classical optical character recognition (OCR). The goal is to identify the author of the text in two different modes: text dependent and text independent.…”

Learning Discriminative Factorized Subspaces With Application to Touchscreen Biometrics

“…Touchscreen biometrics provides a novel way to learn a unique signature of an individual's interaction with the device by studying their swipe gestures. Encouraging results are reported using touchscreen signals as a biometrics especially on mobile systems [1], [2], [3].…”

iSignDB: A database for smartphone signature biometrics

“…Each sample has image of the signature along with sensor readings. Some of the publicly available smartphone biometric signature databases are DooDB [2] , MOBISIG [3] , eBioSign DS 2 [7] , etc. in which at least acceleration sensor reading is present but the iSignDB ensures these five of the sensor readings (acceleration, angular velocity, magnetic field, orientation, position) under each sample.…”