Title: | Using recurrent neural network for hash function generation |
Authors: | Turčaník, Michal |
Citation: | 2017 International Conference on Applied Electronics: Pilsen, 5th – 6th September 2017, Czech Republic, p.253-256. |
Issue Date: | 2017 |
Publisher: | Západočeská univerzita v Plzni |
Document type: | konferenční příspěvek conferenceObject |
URI: | http://hdl.handle.net/11025/35448 |
ISBN: | 978–80–261–0641–8 (Print) 978–80–261–0642–5 (Online) |
ISSN: | 1803–7232 (Print) 1805–9597 (Online) |
Keywords: | hashovací funkce;opakující se neuronová síť |
Keywords in different language: | hash function;recurrent neural network |
Abstract in different language: | Effective generation of hash function is very important for an achievement of a security of today networks. A cryptographic hash function is a transformation that takes an input and returns a fixed-size value, which is called the hash value. A recurrent neural network, as a possible approach, could be used for the hash function generation. The performance of the recurrent neural network (RNN) was validated by software implementation of RNN for given network configuration. The principles of recurrent neural networks and the possibility of using recurrent neural network for hashing are presented in the article. For analysis of RNN were created testing sets on the base of several examples of general texts. In the paper were tested RNNs with three layers. |
Rights: | © Západočeská univerzita v Plzni |
Appears in Collections: | Applied Electronics 2017 Applied Electronics 2017 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Turčaník.pdf | Plný text | 358,39 kB | Adobe PDF | View/Open |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/35448
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.