REAF: replacing exponential activation function to prevent side-channel analysis

DOI10.1007/978-981-96-5566-3_14MaRDI QIDQ6877464zbMATH OpenFDO

Authors Joonsup Kim, Dongjun Park, GyuSang Kim, Sujin Park, Daehyeon Bae, Heeseok Kim, Seokie Hong

Publication date 8 January 2026

Full work available at URL https://doi.org/10.1007/978-981-96-5566-3_14

zbMATH Keywords

activation functionartificial intelligencedeep learningmaskingneural networkpower analysisside channel analysis

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Artificial neural networks and deep learning (68T07) Cryptography (94A60)

Cites work

• Advances in Cryptology - CRYPTO 2003
• Cryptographic Hardware and Embedded Systems - CHES 2004
• High-order conversion from Boolean to arithmetic masking
• scientific article; zbMATH DE number 1418307 (Why is no real title available?)
• Leakage assessment methodology. A clear roadmap for side-channel evaluations
• Protecting AES with Shamir's secret sharing scheme
• Towards sound approaches to counteract power-analysis attacks

This page was built for publication: REAF: replacing exponential activation function to prevent side-channel analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6877464)