How to fool a black box machine learning based side-channel security evaluation

DOI10.1007/S12095-021-00479-XMaRDI QIDQ2120993zbMATH OpenOpenAlexFDO

Authors Charles-Henry Bertrand Van Ouytsel, Olivier Bronchain, Gaëtan Cassiers, François-Xavier Standaert

Publication date 1 April 2022

Published in Cryptography and Communications (Search for Journal in Brave)

Full work available at URL http://hdl.handle.net/2078.1/247935

zbMATH Keywords

black-box side-channel security evaluationmachine learning security

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Cryptography (94A60) Computer security (68M25)

Recommendations

• Against deep learning side-channel attacks
• Climbing down the hierarchy: hierarchical classification for machine learning side-channel attacks
• Power analysis attack: an approach based on machine learning
• A systematic appraisal of side channel evaluation strategies
• Reinforcement learning-based design of side-channel countermeasures

Cites work

• A Unified Framework for the Analysis of Side-Channel Key Recovery Attacks
• A formal study of power variability issues and side-channel attacks for nanoscale devices
• Breaking cryptographic implementations using deep learning techniques
• Consolidating masking schemes
• Convolutional neural networks with data augmentation against jitter-based countermeasures. Profiling attacks without pre-processing
• Does My Device Leak Information? An a priori Statistical Power Analysis of Leakage Detection Tests
• From improved leakage detection to the detection of points of interests in leakage traces
• How fast can higher-order masking be in software?
• Making Masking Security Proofs Concrete
• On the performance of convolutional neural networks for side-channel analysis
• Scikit-learn: machine learning in Python
• The Myth of Generic DPA…and the Magic of Learning
• Topics in Cryptology – CT-RSA 2004
• Towards sound approaches to counteract power-analysis attacks

Cited in

(2)

• Reinforcement learning-based design of side-channel countermeasures
• Climbing down the hierarchy: hierarchical classification for machine learning side-channel attacks

Describes a project that uses

Uses Software

• Scikit
• PRMLT

This page was built for publication: How to fool a black box machine learning based side-channel security evaluation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2120993)