Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 988936

Improving Side-Channel Analysis Through Semi- supervised Learning


Picek, Stjepan; Heuser, Annelie; Jovic, Alan; Knezevic, Karlo; Richmond, Tania
Improving Side-Channel Analysis Through Semi- supervised Learning // 17th Smart Card Research and Advanced Application Conference / Bilgin, Begül ; Fischer, Jean-Bernard (ur.).
Švicarska: Springer International Publishing, 2019. str. 35-50 doi:10.1007/978-3-030-15462-2_3 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


CROSBI ID: 988936 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Improving Side-Channel Analysis Through Semi- supervised Learning

Autori
Picek, Stjepan ; Heuser, Annelie ; Jovic, Alan ; Knezevic, Karlo ; Richmond, Tania

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

ISBN
978-3-030-15461-5

Skup
17th Smart Card Research and Advanced Application Conference

Mjesto i datum
Montpellier, Francuska, 12.-14.11.2018

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Side-channel analysis, Profiled attacks, Machine learning, Semi-supervised learning

Sažetak
The profiled side-channel analysis represents the most powerful category of side-channel attacks. In this context, the security evaluator (i.e., attacker) gains access to a profiling device to build a precise model which is used to attack another device in the attacking phase. Mostly, it is assumed that the attacker has significant capabilities in the profiling phase, whereas the attacking phase is very restricted. We step away from this assumption and consider an attacker restricted in the profiling phase, while the attacking phase is less limited. We propose the concept of semi-supervised learning for side-channel analysis, where the attacker uses a small number of labeled measurements from the profiling phase as well as the unlabeled measurements from the attacking phase to build a more reliable model. Our results show that the semi-supervised concept significantly helps the template attack (TA) and its pooled version (TA_p). More specifically, for low noise scenario, the results for machine learning techniques and TA are often improved when only a smaller number of measurements is available in the profiling phase, while there is no significant difference in scenarios where the supervised set is large enough for reliable classification. For medium to high noise scenario, TA_p and multilayer perceptron results are improved for the majority of inspected dataset sizes, while for high noise scenarios, we show a small improvement for TA_p, Naive Bayes and multilayer perceptron approaches for most inspected dataset sizes. Current results go in favor of using semi- supervised learning, especially self-training approach, in side- channel attacks.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo



POVEZANOST RADA


Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb

Profili:

Avatar Url Karlo Knežević (autor)

Avatar Url Alan Jović (autor)

Avatar Url Stjepan Picek (autor)

Poveznice na cjeloviti tekst rada:

Pristup cjelovitom tekstu rada doi link.springer.com

Citiraj ovu publikaciju:

Picek, Stjepan; Heuser, Annelie; Jovic, Alan; Knezevic, Karlo; Richmond, Tania
Improving Side-Channel Analysis Through Semi- supervised Learning // 17th Smart Card Research and Advanced Application Conference / Bilgin, Begül ; Fischer, Jean-Bernard (ur.).
Švicarska: Springer International Publishing, 2019. str. 35-50 doi:10.1007/978-3-030-15462-2_3 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Picek, S., Heuser, A., Jovic, A., Knezevic, K. & Richmond, T. (2019) Improving Side-Channel Analysis Through Semi- supervised Learning. U: Bilgin, B. & Fischer, J. (ur.)17th Smart Card Research and Advanced Application Conference doi:10.1007/978-3-030-15462-2_3.
@article{article, year = {2019}, pages = {35-50}, DOI = {10.1007/978-3-030-15462-2\_3}, keywords = {Side-channel analysis, Profiled attacks, Machine learning, Semi-supervised learning}, doi = {10.1007/978-3-030-15462-2\_3}, isbn = {978-3-030-15461-5}, title = {Improving Side-Channel Analysis Through Semi- supervised Learning}, keyword = {Side-channel analysis, Profiled attacks, Machine learning, Semi-supervised learning}, publisher = {Springer International Publishing}, publisherplace = {Montpellier, Francuska} }
@article{article, year = {2019}, pages = {35-50}, DOI = {10.1007/978-3-030-15462-2\_3}, keywords = {Side-channel analysis, Profiled attacks, Machine learning, Semi-supervised learning}, doi = {10.1007/978-3-030-15462-2\_3}, isbn = {978-3-030-15461-5}, title = {Improving Side-Channel Analysis Through Semi- supervised Learning}, keyword = {Side-channel analysis, Profiled attacks, Machine learning, Semi-supervised learning}, publisher = {Springer International Publishing}, publisherplace = {Montpellier, Francuska} }

Časopis indeksira:


  • Scopus


Citati:





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font