Non-Invasive Challenge Response Authentication for Voice Transactions with Smart Home Behavior
Smart speakers, such as Alexa and Google Home, support daily activities in smart home environments. Even though voice commands enable friction-less interactions, existing financial transaction authorization mechanisms hinder usability. A non-invasive authorization by leveraging presence and light se...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/22/6563 |
| _version_ | 1797547676053536768 |
|---|---|
| author | Victor Hayashi Wilson Ruggiero |
| author_facet | Victor Hayashi Wilson Ruggiero |
| author_sort | Victor Hayashi |
| collection | DOAJ |
| description | Smart speakers, such as Alexa and Google Home, support daily activities in smart home environments. Even though voice commands enable friction-less interactions, existing financial transaction authorization mechanisms hinder usability. A non-invasive authorization by leveraging presence and light sensors’ data is proposed in order to replace invasive procedure through smartphone notification. The Coloured Petri Net model was created for synthetic data generation, and one month data were collected in test bed with real users. Random Forest machine learning models were used for smart home behavior information retrieval. The LSTM prediction model was evaluated while using test bed data, and an open dataset from CASAS. The proposed authorization mechanism is based on Physical Unclonable Function usage as a random number generator seed in a Challenge Response protocol. The simulations indicate that the proposed scheme with specialized autonomous device could halve the total response time for low value financial transactions triggered by voice, from 7.3 to 3.5 s in a non-invasive manner, maintaining authorization security. |
| first_indexed | 2024-03-10T14:47:28Z |
| format | Article |
| id | doaj.art-2125115d866442c09df8082a3e493381 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T14:47:28Z |
| publishDate | 2020-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-2125115d866442c09df8082a3e4933812023-11-20T21:14:39ZengMDPI AGSensors1424-82202020-11-012022656310.3390/s20226563Non-Invasive Challenge Response Authentication for Voice Transactions with Smart Home BehaviorVictor Hayashi0Wilson Ruggiero1Polytechnic School, University of São Paulo, São Paulo 05508-010, BrazilPolytechnic School, University of São Paulo, São Paulo 05508-010, BrazilSmart speakers, such as Alexa and Google Home, support daily activities in smart home environments. Even though voice commands enable friction-less interactions, existing financial transaction authorization mechanisms hinder usability. A non-invasive authorization by leveraging presence and light sensors’ data is proposed in order to replace invasive procedure through smartphone notification. The Coloured Petri Net model was created for synthetic data generation, and one month data were collected in test bed with real users. Random Forest machine learning models were used for smart home behavior information retrieval. The LSTM prediction model was evaluated while using test bed data, and an open dataset from CASAS. The proposed authorization mechanism is based on Physical Unclonable Function usage as a random number generator seed in a Challenge Response protocol. The simulations indicate that the proposed scheme with specialized autonomous device could halve the total response time for low value financial transactions triggered by voice, from 7.3 to 3.5 s in a non-invasive manner, maintaining authorization security.https://www.mdpi.com/1424-8220/20/22/6563smart homemachine learningauthenticationsimulationtest bed |
| spellingShingle | Victor Hayashi Wilson Ruggiero Non-Invasive Challenge Response Authentication for Voice Transactions with Smart Home Behavior Sensors smart home machine learning authentication simulation test bed |
| title | Non-Invasive Challenge Response Authentication for Voice Transactions with Smart Home Behavior |
| title_full | Non-Invasive Challenge Response Authentication for Voice Transactions with Smart Home Behavior |
| title_fullStr | Non-Invasive Challenge Response Authentication for Voice Transactions with Smart Home Behavior |
| title_full_unstemmed | Non-Invasive Challenge Response Authentication for Voice Transactions with Smart Home Behavior |
| title_short | Non-Invasive Challenge Response Authentication for Voice Transactions with Smart Home Behavior |
| title_sort | non invasive challenge response authentication for voice transactions with smart home behavior |
| topic | smart home machine learning authentication simulation test bed |
| url | https://www.mdpi.com/1424-8220/20/22/6563 |
| work_keys_str_mv | AT victorhayashi noninvasivechallengeresponseauthenticationforvoicetransactionswithsmarthomebehavior AT wilsonruggiero noninvasivechallengeresponseauthenticationforvoicetransactionswithsmarthomebehavior |