Learning when to stop: a mutual information approach to prevent overfitting in profiled side-channel analysis

DOI10.1007/978-3-030-89915-8_3zbMath1491.68038OpenAlexW3210816702MaRDI QIDQ2145285

Stjepan Picek, Ileana Buhan, Guilherme Perin

Publication date: 17 June 2022

Full work available at URL: https://doi.org/10.1007/978-3-030-89915-8_3

zbMATH Keywords

neural networksmutual informationside-channel analysisinformation bottleneckoverfitting

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Cryptography (94A60) Computer security (68M25)

Related Items (1)

Focus is key to success: a focal loss function for deep learning-based side-channel analysis

Cites Work

• Unnamed Item
• Profiled power analysis attacks using convolutional neural networks with domain knowledge
• Breaking cryptographic implementations using deep learning techniques
• Online performance evaluation of deep learning networks for profiled side-channel analysis
• Leakage certification revisited: bounding model errors in side-channel security evaluations
• A Unified Framework for the Analysis of Side-Channel Key Recovery Attacks
• How to Compare Profiled Side-Channel Attacks?
• Convolutional Neural Networks with Data Augmentation Against Jitter-Based Countermeasures
• On the information bottleneck theory of deep learning
• Gradient visualization for general characterization in profiling attacks

This page was built for publication: Learning when to stop: a mutual information approach to prevent overfitting in profiled side-channel analysis