Home > Search Results: keywords:"DLSCA"
Search:
Search Tips :: Advanced Search
Search collections:
Sort by: Display results: Output format:
National Repository of Grey Literature 1 records found  Search took 0.01 seconds. 
Side-channel cryptanalysis using deep learning methods
 Matuška, Jakub ; Martinásek, Zdeněk (referee) ; Sikora, Pavel (advisor)
Cryptographic systems are getting unbreakable on paper. Therefore attacks on the implementations using side-channels are getting in front of others. Especially when neural networks (NN) got involved in this field. With deep learning, these attacks can recover secret keys even on implementations with countermeasures. Deep learning assisted sidechannel analysis (DL-SCA) dominated this field over the statistical methods. That is why it is important to understand its concepts. This thesis will showcase these methods and introduce some new tools regarding correlation power analysis (CPA) and the training of NNs. An attack on ASCAD dataset will take place and the proposed NN to conduct this attack will be evaluated against other models using proper metrics. Lastly, improvements to SITM (See-In-The-Middle) attack using deep learning are proposed and implemented in the console application.
Detailed record

Interested in being notified about new results for this query?
Subscribe to the RSS feed.
Digital Repository :: Search :: Submit :: Personalize :: Help
Powered by Invenio v1.1.2
Maintained by admin.invenio@techlib.cz
This site is also available in the following languages:
Česky  English