Wyniki wyszukiwania - BazTech

1

Uczenie maszynowe z ochroną prywatności danych

Sobolak Kamil, Chołda Piotr

Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne

|

2023

|

nr 4

113--116

PL

Porównano różne metody służące do zapewniania prywatności w przypadku przetwarzania danych z użyciem uczenia maszynowego. Wybrano najbardziej adekwatne metody: szyfrowanie homomorficzne, prywatność różnicowa, metoda uczenia federacyjnego. Efektywność przedstawionych algorytmów została ujęta ilościowo za pomocą powszechnie używanych metryk: funkcji kosztu dla jakości procesu uczenia, dokładności dla klasyfikacji i współczynnika determinacji dla regresji.

EN

Various methods for ensuring privacy in machine learning based data processing were compared. The most suitable methods have been selected: homomorphic encryption, differential privacy, and federated learning. The effectiveness of the presented algorithms was quantified using commonly used metrics: cost function for the quality of the learning process, accuracy for classification, and coefficient of determination for regression.

2

A cryptographic security mechanism for dynamic groups for public cloud environments

Malviya Sheenal, Dave Sourabh, Bandhu Kailash Chandra, Litoriya Ratnesh

Journal of Automation Mobile Robotics and Intelligent Systems

|

2022

|

Vol. 16, No. 2

46--54

EN

Cloud computing has emerged as a significant technology domain, primarily due to the emergence of big data, machine learning, and quantum computing applications. While earlier, cloud computing services were focused mainly on providing storage and some infrastructures/ platforms for applications, the need to advance computational power analysis of massive datasets. It has made cloud computing almost inevitable from most client-based applications, mobile applications, or web applications. The allied challenge to protect data shared from and to cloud-based platforms has cropped up with the necessity to access public clouds. While conventional cryptographic algorithms have been used for securing and authenticating cloud data, advancements in cryptanalysis and access to faster computation have led to possible threats to the traditional security of cloud mechanisms. This has led to extensive research in homomorphic encryption pertaining to cloud security. In this paper, a security mechanism is designed targeted towards dynamic groups using public clouds. Cloud security mechanisms generally face a significant challenge in terms of overhead, throughput, and execution time to encrypt data from dynamic groups with frequent member addition and removal. A two-stage homomorphic encryption process is proposed for data security in this paper. The performance of the proposed system is evaluated in terms of the salient cryptographic metrics, which are the avalanche effect, throughput, and execution time. A comparative analysis with conventional cryptographic algorithms shows that the proposed system outperforms them regarding the cryptographic performance metrics.

3

Block Cipher Based Public Key Encryption via Indistinguishability Obfuscation

Horubała A., Waszkiewicz D., Andrzejczak M., Sapiecha P.

International Journal of Electronics and Telecommunications

|

2018

|

Vol. 64, No. 2

173--178

EN

The article is devoted to generation techniques of the new public key crypto-systems, which are based on application of indistinguishability obfuscation methods to selected private key crypto-systems. The techniques are applied to symmetric key crypto-system and the target system is asymmetric one. As an input for our approach an implementation of symmetric block cipher with a given private-key is considered. Different obfuscation methods are subjected to processing. The target system would be treated as a public-key for newly created public crypto-system. The approach seems to be interesting from theoretical point of view. Moreover, it can be useful for information protection in a cloud-computing model.

4

Data confidentiality and computations hiding in cloud services for public administration

Horubała A., Waszkiewicz D., Andrzejczak M., Sapiecha P.

Computer Science and Mathematical Modelling

|

2018

|

No. 7

11--18

EN

Cloud services are gaining interest and are very interesting option for public administration. Although, there is a lot of concern about security and privacy of storing personal data in cloud. In this work mathematical tools for securing data and hiding computations are presented. Data privacy is obtained by using homomorphic encryption schemes. Computation hiding is done by algorithm cryptographic obfuscation. Both primitives are presented and their application for public administration is discussed.

PL

Chmura obliczeniowa zyskuje coraz większą popularność i staje się ciekawą alternatywą do wykorzystania w administracji publicznej. Istnieje jednak wiele obaw co do bezpieczeństwa i prywatności przechowywanych w chmurze danych osobowych. W tej pracy zaprezentowano matematyczne narzędzia zabezpieczania danych oraz ukrywania obliczeń. Prywatność danych uzyskuje się poprzez wykorzystanie szyfrowania homomorficznego, natomiast ukrywanie danych poprzez obfuskację kryptograficzną. Oba prymitywy zostały zaprezentowane oraz omówiono ich zastosowanie dla administracji publicznej.