Semi-Supervised Template Attack
Side channel attacks take advantage of the information leak-age in a cryptographic device. A template attack is a family of side channel attacks which is reputed to be extremely effective. This kind of attacks supposes that the attacker can fully control a cryptographic de-vice before attacking a similar one. In this paper, the authors propose a method based on a semi-supervised learning strategy to relax this assumption. The effectiveness of their proposal is confirmed by software simulations as well as by experiments on a 8-bit microcontroller.