Arutyun Avetisyan

Arutyun Avetisyan

Auto-generated profile, based on publicly available information

Arutyun Avetisyan

Ivannikov Institute for System Programming of the Russian Academy of Sciences

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 March 2021 in Peer-to-Peer Networking and Applications
Verified
Journal Article
Open access
PDF file
BPBernardo Pulido-Gaytan
Bernardo Pulido-Gaytan
Andrei TchernykhAndrei Tchernykh
Andrei Tchernykh
JCJorge M. Cortés-Mendoza
Jorge M. Cortés-Mendoza
Mikhail BabenkoMikhail Babenko
Mikhail Babenko
GRGleb Radchenko
Gleb Radchenko
ADAlexander Yu Drozdov
Alexander Yu Drozdov
Classical machine learning modeling demands considerable computing power for internal calculations and training with big data in a reasonable amount of time. In recent years, clouds provide services to facilitate this process, but it introduces new security threats of data breaches. Modern encryption techniques ensure security and are considered as the best option to protect stored data and data in transit from an unauthorized third-party. However, a decryption process is necessary when the data must be processed or analyzed, falling into the initial problem of data vulnerability. Fully Homomorphic Encryption (FHE) is considered the holy grail of cryptography. It allows a non-trustworthy third-party resource to process encrypted information without disclosing confidential data. In this paper, we analyze the fundamental concepts of FHE, practical implementations, state-of-the-art approaches, limitations, advantages, disadvantages, potential applications, and development tools focusing on neural networks. In recent years, FHE development demonstrates remarkable progress. However, current literature in the homomorphic neural networks is almost exclusively addressed by practitioners looking for suitable implementations. It still lacks comprehensive and more thorough reviews. We focus on the privacy-preserving homomorphic encryption cryptosystems targeted at neural networks identifying current solutions, open issues, challenges, opportunities, and potential research directions.

16 March 2020 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
Andrei TchernykhAndrei Tchernykh
Andrei Tchernykh
Mikhail BabenkoMikhail Babenko
Mikhail Babenko
NCNikolay Chervyakov
Nikolay Chervyakov
VMVanessa Miranda-Lopez
Vanessa Miranda-Lopez
AAArutyun Avetisyan
Arutyun Avetisyan
Zhihui DuZhihui Du
Zhihui Du

1 November 2018 in International Journal of Approximate Reasoning
Verified
Journal Article
Closed access
Andrei TchernykhAndrei Tchernykh
Andrei Tchernykh
Mikhail BabenkoMikhail Babenko
Mikhail Babenko
NCNikolay Chervyakov
Nikolay Chervyakov
VMVanessa Miranda-López
Vanessa Miranda-López
VKViktor Kuchukov
Viktor Kuchukov
AAArutyun Avetisyan
Arutyun Avetisyan

1 November 2018 in Programming and Computer Software
Verified
Journal Article
Closed access
PDF file
EFEnzo Fabbiani
Enzo Fabbiani
Sergio NesmachnowSergio Nesmachnow
Sergio Nesmachnow
JTJamal Toutouh
Jamal Toutouh
Andrei TchernykhAndrei Tchernykh
Andrei Tchernykh
AAArutyun Avetisyan
Arutyun Avetisyan
GRGleb Radchenko
Gleb Radchenko
Knowing the mobility patterns of citizens using public transportation is an important issue for modern smart cities. Mobility information is crucial for designing and planning an urban...

21 September 2014 in Programming and Computer Software
Verified
Journal Article
Closed access
PDF file
VIV. P. Ivannikov
V. P. Ivannikov
ABA. A. Belevantsev
A. A. Belevantsev
ABA. E. Borodin
A. E. Borodin
VIV. N. Ignatiev
V. N. Ignatiev
DZD. M. Zhurikhin
D. M. Zhurikhin
AAA. I. Avetisyan
A. I. Avetisyan
This paper describes Svace, a tool for static program analysis developed at the Institute for Systems Programming, Russian Academy of Sciences. This tool allows one to find defects and potential vulnerabilities in the source program code written in C/C++ languages. The main features of the tool are simplicity of use, wide variety of supported types of warnings, scalability up to programs of millions of code lines, and acceptable quality of analysis (30–80% of true positive warnings).

1 January 2006 in Lecture Notes in Computer Science
Verified
Book Chapter
Closed access
PDF file
Andrei TchernykhAndrei Tchernykh
Andrei Tchernykh
JRJuan Manuel Ramírez
Juan Manuel Ramírez
AAArutyun Avetisyan
Arutyun Avetisyan
NKNikolai Kuzjurin
Nikolai Kuzjurin
DGDmitri Grushin
Dmitri Grushin
SZSergey Zhuk
Sergey Zhuk