Back to Search
Start Over
On the Importance of Pooling Layer Tuning for Profiling Side-Channel Analysis
- Source :
- Applied Cryptography and Network Security Workshops-ACNS 2021 Satellite Workshops, AIBlock, AIHWS, AIoTS, CIMSS, Cloud S and P, SCI, SecMT, and SiMLA, 2021, Proceedings, Lecture Notes in Computer Science ISBN: 9783030816445, ACNS Workshops
- Publication Year :
- 2021
-
Abstract
- In recent years, the advent of deep neural networks opened new perspectives for security evaluations with side-channel analysis. Profiling attacks now benefit from capabilities offered by convolutional neural networks, such as dimensionality reduction and the inherent ability to reduce the trace desynchronization effects. These neural networks contain at least three types of layers: convolutional, pooling, and dense layers. Although the definition of pooling layers causes a large impact on neural network performance, a study on pooling hyperparameters effect on side-channel analysis is still not provided in the academic community. This paper provides extensive experimental results to demonstrate how pooling layer types and pooling stride and size affect the profiling attack performance with convolutional neural networks. Additionally, we demonstrate that pooling hyperparameters can be larger than usually used in related works and still keep good performance for profiling attacks on specific datasets.
- Subjects :
- Profiling (computer programming)
Pooling
Artificial neural network
Computer science
business.industry
Side-channel analysis
Deep learning
Dimensionality reduction
computer.software_genre
Convolutional neural network
Convolutional neural networks
Data mining
Side channel attack
Artificial intelligence
business
computer
TRACE (psycholinguistics)
Subjects
Details
- Language :
- English
- ISBN :
- 978-3-030-81644-5
- ISSN :
- 03029743
- ISBNs :
- 9783030816445
- Database :
- OpenAIRE
- Journal :
- Applied Cryptography and Network Security Workshops - ACNS 2021 Satellite Workshops, AIBlock, AIHWS, AIoTS, CIMSS, Cloud S and P, SCI, SecMT, and SiMLA, 2021, Proceedings
- Accession number :
- edsair.doi.dedup.....e9d23f99b61b805de7ec62f81e5150ca