Muhammad Muaaz

Influence of different walking speeds and surfaces on accelerometer-based biometric gait recognition

This paper gives an insight about the influence of different walking speeds (slow, normal and fast) and surfaces (flat carpeted, grass, gravel and inclined) on gait recognition. Gait recognition is a type of biometric authentication that operates on behavioral characteristics of human beings. This research utilizes wearable sensors, and we have used a commercially available mobile device. Gait data is collected from 48 subjects for six different walk settings in two sessions on different days to measure same-day and cross-day performance. Gait cycles are extracted and compared using dynamic time warping as distance metric. Different parameter settings are evaluated to optimize the cycle extraction process.

An Analysis of Different Approaches to Gait Recognition Using Cell Phone Based Accelerometers

Biometric gait authentication using Personal Mobile Device (PMD) based accelerometer sensors offers a user-friendly, unobtrusive, and periodic way of authenticating individuals on PMD. In this paper, we present a technique for gait cycle extraction by incorporating the Piecewise Linear Approximation (PLA) technique. We also present two new approaches to classify gait features extracted from the cycle-based segmentation by using Support Vector Machines (SVMs); a) pre-computed data matrix, b) pre-computed kernel matrix. In the first approach, we used Dynamic Time Warping (DTW) distance to compute data matrices, and in the later DTW is used for constructing an elastic similarity measure based kernel function called Gaussian Dynamic Time Warp (GDTW) kernel. Both approaches utilize the DTW similarity measure and can be used for classifying equal length gait cycles, as well as different length gait cycles. To evaluate our approaches we used normal walk biometric gait data of 51 participants. This gait data is collected by attaching a PMD to the belt around the waist, on the right-hand side of the hip. Results show that these new approaches need to be studied more, and potentially lead us to design more robust and reliable gait authentication systems using PMD based accelerometer sensor.

Diversity in locked and unlocked mobile device usage

We analyze locked and unlocked mobile device usage of 1 960 Android smartphones. Based on approximately 10TB of mobile device data logs collected by the Device Analyzer project, we derive 6.9 million usage sessions using a screen power state machine based approach. From these session we examine the number of interactions per day, the average interaction duration as well as the total daily device usage time. Findings indicate that on average users interact with their devices 117 minutes a day, separated over 57 interactions -- while unlocking their device only 43% of the time (e. g. to check for notifications).

Orientation Independent Cell Phone Based Gait Authentication

Gait authentication using a cell phone based accelerometer sensor offers an unobtrusive, user-friendly, and periodic way of authenticating individuals on their cell phones. In this study, we present an approach to deal with inevitable errors induced by continuously changing sensor orientation and other noise under a realistic scenario (when the phone is placed inside the trouser pockets and the user is walking) by using the magnitude data of tri-axes accelerometer and wavelet based noise elimination modules. This study utilizes a gait data set of 35 participants collected at their respective normal walking pace in two different sessions with an average gap of 25 days between the sessions.

ShakeUnlock: Securely Unlock Mobile Devices by Shaking them Together

The inherent weakness of typical mobile device unlocking approaches (PIN, password, graphic pattern) is that they demand time and attention, leading a majority of end users to disable them, effectively lowering device security. We propose a method for unlocking mobile devices by shaking them together, implicitly passing the unlocked state from one device to another. One obvious use case includes a locked mobile phone and a wrist watch, which remains unlocked as long as strapped to the users wrist. Shaking both devices together generates a one-time unlocking event for the phone without the user interacting with the screen. We explicitly analyze the usability critical impact of shaking duration with respect to the level of security. Results indicate that unlocking is possible with a true match rate of 0.795 and true non match rate of 0.867 for a shaking duration as short as two seconds.

Smartphone-Based Gait Recognition: From Authentication to Imitation

This work evaluates the security strength of a smartphone-based gait recognition system against zero-effort and live minimal-effort impersonation attacks under realistic scenarios. For this purpose, we developed an Android application, which uses a smartphone-based accelerometer to capture gait data continuously in the background, but only when an individual walks. Later, it analyzes the recorded gait data and establishes the identity of an individual. At first, we tested the performance of this system against zero-effort attacks by using a dataset of 35 participants. Later, live impersonation attacks were performed by five professional actors who are specialized in mimicking body movements and body language. These attackers were paired with their physiologically close victims, and they were given live audio and visual feedback about their latest impersonation attempt during the whole experiment. No false positives under impersonation attacks, indicate that mimicry does not improve chances of attackers being accepted by our gait authentication system. In 29 percent of total impersonation attempts, when attackers walked like their chosen victim, they lost regularity between their steps which makes impersonation even harder for attackers.

Cross Pocket Gait Authentication Using Mobile Phone Based Accelerometer Sensor

Gait authentication using mobile phone based accelerometer sensors offers an implicit way of authenticating users to their mobile devices. This study explores gait authentication performance under a realistic scenario if gait template and gait test data belongs to left and right side front pocket of the trousers. To simulate this scenario, we used two identical (model, build, and vendor) Android mobile phones to record cross pocket biometric gait data from 35 participants (29 male and 6 female) in two different sessions. Both datasets (left and right pocket) are processed and segmented using the same approach. Our results show that biometric gait performance not only decreases over the time but it is also highly influenced by the placement of the mobile device or the sensor capturing gait data. High number of False Non Matches (FNMR) in cross pocket scenario indicate a significant asymmetry in leg muscle strength.

Confidence and Risk Estimation Plugins for Multi-Modal Authentication on Mobile Devices using CORMORANT

Mobile devices, ubiquitous in modern lifestyle, embody and provide convenient access to our digital lives. Being small and mobile, they are easily lost or stole, therefore require strong authentication to mitigate the risk of unauthorized access. Common knowledge-based mechanism like PIN or pattern, however, fail to scale with the high frequency but short duration of device interactions and ever increasing number of mobile devices carried simultaneously. To overcome these limitations, we present CORMORANT, an extensible framework for risk-aware multi-modal biometric authentication across multiple mobile devices that offers increased security and requires less user interaction.

Accelerometer based Gait Recognition using Adapted Gaussian Mixture Models

Gait authentication using a cell phone based accelerometer sensor offers an unobtrusive, user-friendly, and a periodic way of authenticating individuals to their smartphones. In this paper, we present a GMM-UBM based gait recognition approach for a realistic scenario (when the phone is placed inside the trouser pocket and the user is walking) by using the magnitude data of a smartphone-based tri-axes accelerometer sensor. To evaluate our approach we use a gait data set of 35 participants collected at their respective normal walking pace in two different sessions with an average gap of 25 days between the sessions. We obtained EERs of 3.031%, 11.531%, and 14.393% for the same-day, mix-days, and cross-days, respectively.