Using recurrent neural networks for continuous authentication through gait analysis

Giorgi, Giacomo; Saracino, Andrea; Martinelli, Fabio

doi:10.1016/j.patrec.2021.03.010

Cited by 44 publications

(58 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The basic idea is to capture the three-dimensional time series using a triaxial accelerometer, and GDI is expressed as the cosine similarity of the motion measurement at time t with the lag time signal. Damaševicius et al [ 25 ] used random projections to reduce feature dimensionality to two, followed by computing the Jaccard distance between two probability distributed functions of the derived features for positive identification. Kašys et al [ 26 ] performed user identity verification using linear Support Vector Machine (SVM) classifier on his/her walking activity data captured by the mobile phone.…”

Section: Related Workmentioning

confidence: 99%

“…This method is not appropriate for CNN because CNN is not good at processing one-dimensional signals. Giorgi et al [ 25 ] described a user authentication framework, exploiting inertial sensors and making use of Recurrent Neural Network for deep-learning based classification. However, the difference in results for known identities and unknown identities is quite significant.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Gait-Based Implicit Authentication Using Edge Computing and Deep Learning for Mobile Devices

Zeng

Zhang

Yang

et al. 2021

Sensors

View full text Add to dashboard Cite

Implicit authentication mechanisms are expected to prevent security and privacy threats for mobile devices using behavior modeling. However, recently, researchers have demonstrated that the performance of behavioral biometrics is insufficiently accurate. Furthermore, the unique characteristics of mobile devices, such as limited storage and energy, make it subject to constrained capacity of data collection and processing. In this paper, we propose an implicit authentication architecture based on edge computing, coined Edge computing-based mobile Device Implicit Authentication (EDIA), which exploits edge-based gait biometric identification using a deep learning model to authenticate users. The gait data captured by a device’s accelerometer and gyroscope sensors is utilized as the input of our optimized model, which consists of a CNN and a LSTM in tandem. Especially, we deal with extracting the features of gait signal in a two-dimensional domain through converting the original signal into an image, and then input it into our network. In addition, to reduce computation overhead of mobile devices, the model for implicit authentication is generated on the cloud server, and the user authentication process also takes place on the edge devices. We evaluate the performance of EDIA under different scenarios where the results show that i) we achieve a true positive rate of 97.77% and also a 2% false positive rate; and ii) EDIA still reaches high accuracy with limited dataset size.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Gait-Based Implicit Authentication Using Edge Computing and Deep Learning for Mobile Devices

Zeng

Zhang

Yang

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…One exception is the Human Activity Recognition using Smartphone (UCI-HAR) dataset [40], which is a collection devoted to activity recognition. The dataset has also been utilized for continuous authentication [24]. Another notable exception is the WISDM-HARB dataset, which gathers data on activity patterns to investigate activity identification and authentication using smartphone sensors.…”

Section: Data Acquisitionmentioning

confidence: 99%

“…This study used a data segmentation technique called an overlapping temporal window (OW), which generates data samples by applying a fixed-size window to the sensor data stream. The OW technique is the most often employed in sensor-based HAR and authentication research, with a 50% overlap rate [23,24]. Nevertheless, this sample generation is considerably unbalanced since D t and D t+1 share a percentage of the sensor data.…”

Section: Data Preprocessingmentioning

confidence: 99%

“…This method is based on the established premise that each individual has a particular activity pattern, which can be used to validate specific uniqueness. Previous research [22][23][24] used basic activity patterns such as walking and climbing and descending stairs as cognitive biometric data for continuous user authentication. Evaluating a vast number of various everyday life activities is a research gap for various reasons.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Approaches for Continuous Authentication Based on Activity Patterns Using Mobile Sensing

Jitpattanakul

2021

Sensors

View full text Add to dashboard Cite

Smartphones as ubiquitous gadgets are rapidly becoming more intelligent and context-aware as sensing, networking, and processing capabilities advance. These devices provide users with a comprehensive platform to undertake activities such as socializing, communicating, sending and receiving e-mails, and storing and accessing personal data at any time and from any location. Nowadays, smartphones are used to store a multitude of private and sensitive data including bank account information, personal identifiers, account passwords and credit card information. Many users remain permanently signed in and, as a result, their mobile devices are vulnerable to security and privacy risks through assaults by criminals. Passcodes, PINs, pattern locks, facial verification, and fingerprint scans are all susceptible to various assaults including smudge attacks, side-channel attacks, and shoulder-surfing attacks. To solve these issues, this research introduces a new continuous authentication framework called DeepAuthen, which identifies smartphone users based on their physical activity patterns as measured by the accelerometer, gyroscope, and magnetometer sensors on their smartphone. We conducted a series of tests on user authentication using several deep learning classifiers, including our proposed deep learning network termed DeepConvLSTM on the three benchmark datasets UCI-HAR, WISDM-HARB and HMOG. Results demonstrated that combining various motion sensor data obtained the highest accuracy and energy efficiency ratio (EER) values for binary classification. We also conducted a thorough examination of the continuous authentication outcomes, and the results supported the efficacy of our framework.

show abstract

Using Biometric Data to Authenticate Tactical Edge Network Users

da Silva Campos,

Dalzochio,

Nunes

et al. 2024

Lecture Notes on Data Engineering and Communications Technologies

View full text Add to dashboard Cite

Using recurrent neural networks for continuous authentication through gait analysis

Cited by 44 publications

References 10 publications

Gait-Based Implicit Authentication Using Edge Computing and Deep Learning for Mobile Devices

Gait-Based Implicit Authentication Using Edge Computing and Deep Learning for Mobile Devices

Deep Learning Approaches for Continuous Authentication Based on Activity Patterns Using Mobile Sensing

Using Biometric Data to Authenticate Tactical Edge Network Users

Contact Info

Product

Resources

About