Deep-learning-based radio-frequency side-channel attack on quantum key distribution

Abstract

Quantum key distribution (QKD) is a technique that allows two distant parties to distribute and share a common secret, which then can be used as a cryptographic key. While mathematical proofs verify the security of perfectly implemented systems, imperfections in real devices allow attackers to retrieve information. This study uses machine-learning techniques to investigate information leakage via radio-frequency emissions of QKD device electronics. The approach allows researchers and engineers to harden devices against attacks.

Topics & Concepts