Skip to main navigation Skip to search Skip to main content

RLND: A ResNet and LSTM Based Neural Distinguisher for Lightweight Block Ciphers

  • Jie Liu*
  • , Junjie Xu
  • , Yunhao Qiu
  • , Qibo Liu
  • *Corresponding author for this work
  • Northwestern Polytechnical University Xian

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Block ciphers are widely used to ensure the security of data in the digital age, yet the techniques for analyzing them continue to advance. Recently, neural distinguishers have garnered significant attention due to their higher accuracy compared to traditional methods when analyzing block ciphers. In this work, we propose a novel neural distinguisher, named RLND, which can extract both spatial and temporal features. Specifically, we design a multi-scale convolutional kernel-based residual network (MSCK-ResNet) to fuse spatial features across different scales through varied receptive fields. To capture temporal dependencies, we construct a multi-layer LSTM (ML-LSTM) module with varying numbers of neurons. The optimal configuration of RLND, including the number of MSCK-ResNet blocks and ML-LSTM layers, is determined experimentally to maximize accuracy. We evaluate the performance of the proposed distinguisher on five lightweight block ciphers, demonstrating that it achieves up to 0.5% and 5.5% higher accuracy with single and multiple ciphertext pairs, respectively. This highlights the strong potential of RLND for practical key recovery.

Original languageEnglish
Title of host publicationApplied Cryptography and Network Security - 24th International Conference, ACNS 2026, Proceedings
EditorsKangkook Jee, Aniket Kate
PublisherSpringer Science and Business Media Deutschland GmbH
Pages186-205
Number of pages20
ISBN (Print)9783032325778
DOIs
StatePublished - 2027
Externally publishedYes
Event24th International Conference on Applied Cryptography and Network Security, ACNS 2026 - Stony Brook, United States
Duration: 22 Jun 202625 Jun 2026

Publication series

NameLecture Notes in Computer Science
Volume16573 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference24th International Conference on Applied Cryptography and Network Security, ACNS 2026
Country/TerritoryUnited States
CityStony Brook
Period22/06/2625/06/26

Keywords

  • Differential analysis
  • Key recovery
  • Lightweight block cipher
  • Neural distinguisher

Fingerprint

Dive into the research topics of 'RLND: A ResNet and LSTM Based Neural Distinguisher for Lightweight Block Ciphers'. Together they form a unique fingerprint.

Cite this