HORIZON TRACE Project
Published August 26, 2025 | Version v1
Conference paper Open

Neural Cryptanalysis of Lightweight Block Ciphers Using Residual MLPs

Authors/Creators

  • 1. Sidroco Holdings Ltd.
  • 2. Sidroco Holdings LTD
  • 3. SIDROCO HOLDINGS Ltd
  • 4. ROR icon Democritus University of Thrace
  • 5. ROR icon Kingston University
  • 6. ROR icon International Hellenic University
  • 7. ROR icon University of Western Macedonia

Description

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. 

Files

542118286_charis_eleftheriadis_Camera_Ready.pdf

Files (445.2 kB)

Name Size Download all
md5:c3da8efe34b2c386066ccb3a9e7a9fd8
445.2 kB Preview Download

Additional details

Funding

European Commission
TRACE - Integration and Harmonization of Logistics Operations 101104278