Fake it till you make it: data augmentation using generative adversarial networks for all the crypto you need on small devices

DOI10.1007/978-3-030-95312-6_13MaRDI QIDQ2152167zbMATH OpenOpenAlexFDO

Authors Naila Mukhtar, Lejla Batina, Stjepan Picek, Yinan Kong

Publication date 6 July 2022

Full work available at URL https://doi.org/10.1007/978-3-030-95312-6_13

zbMATH Keywords

data augmentationsignal processingelliptic curve cryptographyGANsASCADdeep learning-based side-channel attacks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Data encryption (aspects in computer science) (68P25) Cryptography (94A60) Computer security (68M25)

Recommendations

• Generative adversarial networks-based pseudo-random number generator for embedded processors
• Practical Fully Homomorphic Encryption for Fully Masked Neural Networks
• Breaking cryptographic implementations using deep learning techniques

Cites work

• scientific article; zbMATH DE number 1979272 (Why is no real title available?)
• Breaking cryptographic implementations using deep learning techniques
• Convolutional neural networks with data augmentation against jitter-based countermeasures. Profiling attacks without pre-processing
• Deep learning
• Localized electromagnetic analysis of cryptographic implementations
• Online template attack on ECDSA: extracting keys via the other side
• Online template attacks
• Power analysis attack: an approach based on machine learning
• SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination
• The Myth of Generic DPA…and the Magic of Learning

Describes a project that uses

Uses Software

• GitHub
• BigGAN
• SiGAN
• StackGAN
• InfoGAN

This page was built for publication: Fake it till you make it: data augmentation using generative adversarial networks for all the crypto you need on small devices

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2152167)