Browsing by Subject "Applications usage"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Publication
    Open Access
    A supervised ML Biometric Continuous Authentication System for Industry 4.0
    (IEEE, 2022-04-29) Espín López, Juan Manuel; Huertas Celdrán, Alberto; Esquembre, Francisco; Martínez Pérez, Gregorio; Marín-Blázquez, Javier G.; Matemáticas
    Continuous authentication (CA) is a promis- ing approach to authenticate workers and avoid security breaches in the industry, especially in Industry 4.0, where most interaction between workers and devices takes place. However, introducing CA in industries raises unsolved questions regarding machine learning (ML) models: i) its precision and performance, ii) its robustness and iii) the issue about if or when to retrain the models. To answer these questions, this work explores these issues with a proposed supervised vs non-supervised ML-based CA sys- tem that uses sensors, applications statistics, or speaker data collected by the operator’s devices. Experiments show supervised models with Equal Error Rates of 7.28% using sensors data, 9.29% with statistics, and 0.31% with voice, a significant improvement of 71.97%, 62.14%, and 97.08%, respectively, over unsupervised models. Voice is the most robust dimension when adding new workers, with less than 2% of false acceptance rate even if workforce size is doubled.
  • Repository logo
    Publication
    Restricted
    S3 Dataset
    (2021-04-13) Espín López, Juan Manuel; Huertas Celdrán, Alberto; Marín-Blázquez, Javier G.; Esquembre, Francisco; Martínez Pérez, Gregorio; Matemáticas
    The S3 dataset contains the behavior (sensors, statistics of applications, and voice) of 21 volunteers interacting with their smartphones for more than 60 days. The type of users is diverse, males and females in the age range from 18 until 70 have been considered in the dataset generation. The wide range of age is a key aspect, due to the impact of age in terms of smartphone usage. To generate the dataset the volunteers installed a prototype of the smartphone application in on their Android mobile phones. All attributes of the different kinds of data are writed in a vector. The dataset contains the fellow vectors: Sensors: This type of vector contains data belonging to smartphone sensors (accelerometer and gyroscope) that has been acquired in a given windows of time. Each vector is obtained every 20 seconds, and the monitored features are: - Average of accelerometer and gyroscope values. - Maximum and minimum of accelerometer and gyroscope values. - Variance of accelerometer and gyroscope values. - Peak-to-peak (max-min) of X, Y, Z coordinates. - Magnitude for gyroscope and accelerometer. Statistics: These vectors contain data about the different applications used by the user recently. Each vector of statistics is calculated every 60 seconds and contains : - Foreground application counters (number of different and total apps) for the last minute and the last day. - Most common app ID and the number of usages in the last minute and the last day. - ID of the currently active app. - ID of the last active app prior to the current one. - ID of the application most frequently utilized prior to the current application. - Bytes transmitted and received through the network interfaces. Voice: This kind of vector is generated when the microphone is active in a call o voice note. The speaker vector is an embedding, extracted from the audio, and it contains information about the user's identity. This vector, is usually named "x-vector" in the Speaker Recognition field, and it is calculated following the steps detailed in "egs/sitw/v2" for the Kaldi library, with the models available for the extraction of the embedding. A summary of the details of the collected database. - Users: 21 - Sensors vectors: 417.128 - Statistics app's usage vectors: 151.034 - Speaker vectors: 2.720 - Call recordings: 629 - Voice messages: 2.091
  • Thumbnail Image
    Publication
    Open Access
    S3: An AI-Enabled User Continuous Authentication for Smartphones Based on Sensors, Statistics and Speaker Information
    (MDPI, 2021-05-28) Espín López, Juan Manuel; Huertas Celdrán, Alberto; Marín-Blázquez, Javier G.; Esquembre, Francisco; Martínez Pérez, Gregorio; Matemáticas
    Continuous authentication systems have been proposed as a promising solution to au- thenticate users in smartphones in a non-intrusive way. However, current systems have important weaknesses related to the amount of data or time needed to build precise user profiles, together with high rates of false alerts. Voice is a powerful dimension for identifying subjects but its suitability and importance have not been deeply analyzed regarding its inclusion in continuous authentication systems. This work presents the S3 platform, an artificial intelligence-enabled continuous authen- tication system that combines data from sensors, applications statistics and voice to authenticate users in smartphones. Experiments have tested the relevance of each kind of data, explored different strategies to combine them, and determined how many days of training are needed to obtain good enough profiles. Results showed that voice is much more relevant than sensors and applications statistics when building a precise authenticating system, and the combination of individual models was the best strategy. Finally, the S3 platform reached a good performance with only five days of use available for training the users’ profiles. As an additional contribution, a dataset with 21 volun- teers interacting freely with their smartphones for more than sixty days has been created and made available to the community.