Blind Twins: Siamese Networks for Non-Interactive Information Reconciliation
Research output: Contribution to book/Conference proceedings/Anthology/Report › Conference contribution › Contributed › peer-review
Contributors
Abstract
Through Information Reconciliation, two legitimate parties of Channel Reciprocity-based Key Generation assure that they extract the same key from local channel measurements. Current protocols exchange messages: Interactivity both causes delays and energy expenditure, and leaks information about the keying material to adversaries.We suggest non-interactive reconciliation, using a Siamese Network of CNNs that extracts reciprocal and suppresses nonreciprocal components in the measurements. Training and evaluating on real-world and synthetic data, we demonstrate that it blindly achieves higher correlation of the outputs at legitimate parties than the interactive state of the art, thus eliminating cost and information leakage at superior performance.
Details
Original language | English |
---|---|
Title of host publication | 2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications |
Publisher | IEEE TechRxiv |
Pages | 1-7 |
Number of pages | 7 |
ISBN (print) | 978-1-7281-4491-7 |
Publication status | Published - 3 Sept 2020 |
Peer-reviewed | Yes |
Conference
Title | 2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications |
---|---|
Duration | 31 August - 3 September 2020 |
Location | London, UK |
External IDs
Scopus | 85094167312 |
---|
Keywords
Keywords
- Protocols, Feature extraction, Quantization (signal), Channel estimation, Land mobile radio, Privacy, Iterative decoding