Title | ||
---|---|---|
A New Protocol For On-Line User Authentication Based On 1 Out Of N Types Of Personal Data |
Abstract | ||
---|---|---|
In this paper, we propose a new protocol for on-line user authentication based on multiple personal data. Needless to say, some kind of personal data must be used for authentication. In most cases, the type (e.g. finger print and vein) of the personal data is fixed, and authentication is done by comparing the input data with those registered in the system. In this paper, we propose a protocol that allows authentication based on 1 out of n types of personal data. For registration, the user may register 1 out of n types of personal data, and use it for authentication. If n is large, the difficulty for a third party to spoof the original user can be higher because he/she must try a lot of times before getting the correct data type to attack. The basic idea of the proposed protocol is to "normalize" all types of personal data into the same format, and conduct authentication using the same machine learning model. This idea is verified via experiments on several public databases. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/SMC.2018.00133 | 2018 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC) |
Keywords | Field | DocType |
On-line authentication, 1 out of n authentication, machine learning, personal data normalization | Authentication,Information retrieval,Computer science,Third party,Data type,Artificial intelligence,Machine learning | Conference |
ISSN | Citations | PageRank |
1062-922X | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Masato Hashimoto | 1 | 0 | 1.01 |
Ryota Fukuzawa | 2 | 0 | 0.34 |
Qiangfu Zhao | 3 | 214 | 62.36 |
Shota Yamamoto | 4 | 0 | 0.34 |
Kazuma Ishii | 5 | 0 | 0.34 |
Shota Oikawa | 6 | 0 | 0.34 |