Image Based Crypto Public Deposited

http://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/765374492

Descriptions

Attribute NameValues
Creator
Abstract or Summary
  • The ability to create reproducible cryptographically secure keys from temporal environments (e.g., images) has the potential to be a contributor to effective cryptographic mechanisms. Due to the noisy nature of these environments, achieving this goal in a user friendly fashion is a very challenging task, especially since there exists a research gap to create reproducible keys from image data. In this thesis, towards addressing aforementioned challenge, we developed a new image based reproducible key derivation mechanism, which leverages deep learning technique along side with fuzzy-extractor schemes to enable reproducible symmetric key creation from temporal visual environments. Our technique uses deep learning and fuzzy-extractors as fundamental building blocks. Deep learning harnesses patterns in images to minimize the noise, and permit successful utilization of fuzzy-extractor schemes to handle errors by using error-correcting codes. Using these techniques together enables reproducible key generation. We also instantiated our technique to enable three potential use cases: i) Image entropy strengthened authentication, ii) image based password authenticated Diffie-Hellman, and iii) position based cryptography. Along side these potential use cases, we conducted a user study to assess the usability of the provided scheme.
Resource Type
Date Available
Date Copyright
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Non-Academic Affiliation
Keyword
Subject
Rights Statement
Peer Reviewed
Language
Replaces
Additional Information
  • description.provenance : Submitted by Gungor Basa (basag@oregonstate.edu) on 2016-12-09T08:35:53Z No. of bitstreams: 1 BasaGungor2016.pdf: 5599319 bytes, checksum: f8db82d6fb1256078b98f75e0083d612 (MD5)
  • description.provenance : Made available in DSpace on 2016-12-23T19:07:46Z (GMT). No. of bitstreams: 1 BasaGungor2016.pdf: 5599319 bytes, checksum: f8db82d6fb1256078b98f75e0083d612 (MD5) Previous issue date: 2016-12-02
  • description.provenance : Approved for entry into archive by Julie Kurtz(julie.kurtz@oregonstate.edu) on 2016-12-14T19:11:28Z (GMT) No. of bitstreams: 1 BasaGungor2016.pdf: 5599319 bytes, checksum: f8db82d6fb1256078b98f75e0083d612 (MD5)
  • description.provenance : Approved for entry into archive by Laura Wilson(laura.wilson@oregonstate.edu) on 2016-12-23T19:07:46Z (GMT) No. of bitstreams: 1 BasaGungor2016.pdf: 5599319 bytes, checksum: f8db82d6fb1256078b98f75e0083d612 (MD5)

Relationships

Parents:

This work has no parents.

Last modified

Downloadable Content

Download PDF

Items