Motion ID: Human Authentication Approach
- URL: http://arxiv.org/abs/2302.01751v1
- Date: Wed, 25 Jan 2023 09:08:33 GMT
- Title: Motion ID: Human Authentication Approach
- Authors: Aleksei Gavron, Konstantin Belev, Konstantin Kudelkin, Vladislav
Shikhov, Andrey Akushevich, Alexey Fartukov, Vladimir Paramonov, Dmitry
Syromolotov, Artem Makoyan
- Abstract summary: We introduce a novel approach to user authentication called Motion ID.
The method employs motion sensing provided by inertial measurement units (IMUs) to verify the persons identity via short time series of IMU data captured by the mobile device.
- Score: 0.0
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: We introduce a novel approach to user authentication called Motion ID. The
method employs motion sensing provided by inertial measurement units (IMUs),
using it to verify the persons identity via short time series of IMU data
captured by the mobile device. The paper presents two labeled datasets with
unlock events: the first features IMU measurements, provided by six users who
continuously collected data on six different smartphones for a period of 12
weeks. The second one contains 50 hours of IMU data for one specific motion
pattern, provided by 101 users. Moreover, we present a two-stage user
authentication process that employs motion pattern identification and user
verification and is based on data preprocessing and machine learning. The
Results section details the assessment of the method proposed, comparing it
with existing biometric authentication methods and the Android biometric
standard. The method has demonstrated high accuracy, indicating that it could
be successfully used in combination with existing methods. Furthermore, the
method exhibits significant promise as a standalone solution. We provide the
datasets to the scholarly community and share our project code.
Related papers
- No Identity, no problem: Motion through detection for people tracking [48.708733485434394]
We propose exploiting motion clues while providing supervision only for the detections.
Our algorithm predicts detection heatmaps at two different times, along with a 2D motion estimate between the two images.
We show that our approach delivers state-of-the-art results for single- and multi-view multi-target tracking on the MOT17 and WILDTRACK datasets.
arXiv Detail & Related papers (2024-11-25T15:13:17Z) - Multi-Channel Time-Series Person and Soft-Biometric Identification [65.83256210066787]
This work investigates person and soft-biometrics identification from recordings of humans performing different activities using deep architectures.
We evaluate the method on four datasets of multi-channel time-series human activity recognition (HAR)
Soft-biometric based attribute representation shows promising results and emphasis the necessity of larger datasets.
arXiv Detail & Related papers (2023-04-04T07:24:51Z) - DOAD: Decoupled One Stage Action Detection Network [77.14883592642782]
Localizing people and recognizing their actions from videos is a challenging task towards high-level video understanding.
Existing methods are mostly two-stage based, with one stage for person bounding box generation and the other stage for action recognition.
We present a decoupled one-stage network dubbed DOAD, to improve the efficiency for-temporal action detection.
arXiv Detail & Related papers (2023-04-01T08:06:43Z) - mPSAuth: Privacy-Preserving and Scalable Authentication for Mobile Web
Applications [0.0]
mPSAuth is an approach for continuously tracking various data sources reflecting user behavior and estimating the likelihood of the current user being legitimate.
We show that mPSAuth can provide high accuracy with low encryption and communication overhead, while the effort for the inference is increased to a tolerable extent.
arXiv Detail & Related papers (2022-10-07T12:49:34Z) - BehavePassDB: Benchmarking Mobile Behavioral Biometrics [12.691633481373927]
We present a new database, BehavePassDB, structured into separate acquisition sessions and tasks.
We propose and evaluate a system based on Long-Short Term Memory (LSTM) architecture with triplet loss and modality fusion at score level.
arXiv Detail & Related papers (2022-06-06T11:21:15Z) - Mobile Behavioral Biometrics for Passive Authentication [65.94403066225384]
This work carries out a comparative analysis of unimodal and multimodal behavioral biometric traits.
Experiments are performed over HuMIdb, one of the largest and most comprehensive freely available mobile user interaction databases.
In our experiments, the most discriminative background sensor is the magnetometer, whereas among touch tasks the best results are achieved with keystroke.
arXiv Detail & Related papers (2022-03-14T17:05:59Z) - Data-driven behavioural biometrics for continuous and adaptive user
verification using Smartphone and Smartwatch [0.0]
We propose an algorithm to blend behavioural biometrics with multi-factor authentication (MFA)
This work proposes a two-step user verification algorithm that verifies the user's identity using motion-based biometrics.
arXiv Detail & Related papers (2021-10-07T02:46:21Z) - Diverse Knowledge Distillation for End-to-End Person Search [81.4926655119318]
Person search aims to localize and identify a specific person from a gallery of images.
Recent methods can be categorized into two groups, i.e., two-step and end-to-end approaches.
We propose a simple yet strong end-to-end network with diverse knowledge distillation to break the bottleneck.
arXiv Detail & Related papers (2020-12-21T09:04:27Z) - End-to-end User Recognition using Touchscreen Biometrics [11.394909061094463]
The goal was to create an end-to-end system that can transparently identify users using raw data from mobile devices.
In the proposed system data from the touchscreen goes directly to the input of a deep neural network, which is able to decide on the identity of the user.
arXiv Detail & Related papers (2020-06-09T16:38:09Z) - Intra-Camera Supervised Person Re-Identification [87.88852321309433]
We propose a novel person re-identification paradigm based on an idea of independent per-camera identity annotation.
This eliminates the most time-consuming and tedious inter-camera identity labelling process.
We formulate a Multi-tAsk mulTi-labEl (MATE) deep learning method for Intra-Camera Supervised (ICS) person re-id.
arXiv Detail & Related papers (2020-02-12T15:26:33Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.