Multiple-Layer Candidate Sieves Against Serial Cryptographic Implementations

Abstract

The existing multiple-layer candidate sieve exploits collisions to filter the candidates to achieve a much smaller space for easier key recovery, and tries to recover the key ranking at very deep candidate space. However, it leads to enormous computation yet achieves very low success probability. In this paper, we build a novel Simple Multiple-Layer Sieve (SMLS) from Correlation Power Analysis (CPA) and achieve better performance than the existing one. Furthermore, we build two combined sieves named Two-Layer Stacking Sieve (TLSS) and Full-Layer Stacking Sieve (FLSS) since same operations in serial cryptographic implementation generate similar leakage. The experimental results verify their superiority.