2020
DOI: 10.1109/tc.2020.3013196
|View full text |Cite
|
Sign up to set email alerts
|

SCAUL: Power Side-Channel Analysis With Unsupervised Learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
13
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 42 publications
(15 citation statements)
references
References 33 publications
0
13
0
Order By: Relevance
“…Authors in [12] developed a multi-layerperceptron (MLP) NN-based sensitivity analysis to derive the leakage model. The observed traces (measured leaked information) were clustered, then encoded using long-short-term memory (LSTM) autoencoder to provide contextual features (secret keys patterns).…”
Section: Slice Isolationmentioning
confidence: 99%
See 1 more Smart Citation
“…Authors in [12] developed a multi-layerperceptron (MLP) NN-based sensitivity analysis to derive the leakage model. The observed traces (measured leaked information) were clustered, then encoded using long-short-term memory (LSTM) autoencoder to provide contextual features (secret keys patterns).…”
Section: Slice Isolationmentioning
confidence: 99%
“…However, machine-type-communication-generated traffic could be considered for robust interpretations of the dynamics in demands. Later, we discuss additional challenges that pertain to the introduction of ML for RAN-S. We also envisage the incorporation of MLbased information leakage models [11], [12] into RAN-S to tackle the challenge of slice isolation.…”
Section: Introductionmentioning
confidence: 99%
“…Recently, the hardware security research has transferred attention to the machine learning (ML) based profiled attacks and ciphers classification. Support Vector Machine (SVM) [6], Random Forest (RF) [7], and other deep learning [8] based attacks not only perform valid attacks but reduce the concern on POIs.…”
Section: Introductionmentioning
confidence: 99%
“…2017, Eleonora Cagli proposed a point-to-point profiling attack method based on the application of Convolutional Neural Networks (CNN) [9][10][11][12][13][14][15]. It does not need a manually traces realignment nor accurate selection of POIs.…”
Section: Introductionmentioning
confidence: 99%
“…Masure et al [16] investigate the theoretical soundness of Convolutional Neural Networks (CNNs) in the context of side-channel, References [17][18][19] demonstrated successful attacks on Virtex-5 FPGAs using CNNs. On a lightweight implementation of AES on Artix-7 FPGA [20], a non-profiled attack is able to recover the key with 3700 traces. Apart from FPGA, [21] shows the effectiveness of CNN-based side-channel attacks on ASICs.…”
Section: Introductionmentioning
confidence: 99%