Full Program

Neural Cryptanalysis of Lightweight Block Ciphers Using Residual MLPs

Summary:

The security of Internet of Things (IoT) devices
is a growing concern, given their widespread deployment in
environments with limited computational and energy resources.
Lightweight block ciphers, such as SIMON and SPECK, are
designed to provide efficient cryptographic operations while
minimizing computational overhead. However, evaluating their
resilience against emerging attack vectors is vital for maintaining
robust protection. This paper introduces a neural cryptanalysis
approach for evaluating the security of SIMON and SPECK
block ciphers, by leveraging a Residual Multi-Layer Perceptron
(ResMLP) model in order to approximate the encryption and
decryption processes. Experimental results demonstrate the effectiveness of the approach in revealing vulnerabilities, showcasing
its efficiency and scalability in performing neural cryptanalysis
on lightweight block ciphers.

Author(s):

Charis Eleftheriadis    
Sidroco Holdings Ltd
Cyprus

Georgios Andronikidis    
Sidroco Holdings Ltd
Cyprus

Anastasios Lytos    
Sidroco Holdings Ltd
Cyprus

Eleutherios Fountoukidis    
Sidroco Holdings Ltd
Cyprus

Paris-Alexandros Karypidis    
Sidroco Holdings Ltd
Cyprus

Thomas Lagkas    
Department of Computer Science, International Hellenic University
Greece

Vasileios Argyriou    
Department of Networks and Digital Media, Kingston University London
United Kingdom

Ioannis Nanos    
Department of Organisation Management, Marketing and Tourism, International Hellenic University
Greece

Panagiotis Sarigiannidis    
Department of Electrical and Computer Engineering, University of Western Macedonia
Greece