Kirill Morozov

Dr. Kirill Morozov

Department of Computer Science and Engineering, University of North Texas, Denton, TX 76207-7102, USA

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
19 February 2023
Verified
Book Chapter
Closed access
PDF file
ASAbiola Salau
Abiola Salau
RDRam Dantu
Ram Dantu
Kirill MorozovKirill Morozov
Kirill Morozov
KUKritagya Upadhyay
Kritagya Upadhyay
SBSyed Badruddoja
Syed Badruddoja

11 October 2019
Verified
Book Chapter
Closed access
PDF file
YDYvo Desmedt
Yvo Desmedt
SDSabyasachi Dutta
Sabyasachi Dutta
Kirill MorozovKirill Morozov
Kirill Morozov

1 January 2018 in Open Mathematics
Verified
Journal Article
Open access
PDF file
Kirill MorozovKirill Morozov
Kirill Morozov
PRPartha Sarathi Roy
Partha Sarathi Roy
RSRainer Steinwandt
Rainer Steinwandt
RXRui Xu
Rui Xu
We prove that a variant of the Courtois-Finiasz-Sendrier signature is strongly existentially unforgeable under chosen message attack in the random oracle model, assuming hardness of the Permuted Goppa Syndrome Decoding Problem (also known as the Niederreiter problem). In addition, we explicitly show that security against key substitution attacks can be arranged by a standard technique of Menezes and Smart, hashing the public key.

16 November 2025
Verified
Book Chapter
Closed access
PDF file
NCNicolas Chiapputo
Nicolas Chiapputo
YDYvo Desmedt
Yvo Desmedt
Kirill MorozovKirill Morozov
Kirill Morozov

8 October 2025 in arXiv
Verified
Preprint
Open access
PDF file
KCKalyan Cheerla
Kalyan Cheerla
LOLotfi Ben Othmane
Lotfi Ben Othmane
Kirill MorozovKirill Morozov
Kirill Morozov
Machine Learning (ML) is making its way into fields such as healthcare, finance, and Natural Language Processing (NLP), and concerns over data privacy and model confidentiality continue to grow. Privacy-preserving Machine Learning (PPML) addresses this challenge by enabling inference on private data without revealing sensitive inputs or proprietary models. Leveraging Secure Computation techniques from Cryptography, two widely studied approaches in this domain are Fully Homomorphic Encryption (FHE) and Garbled Circuits (GC). This work presents a comparative evaluation of FHE and GC for secure neural network inference. A two-layer neural network (NN) was implemented using the CKKS scheme from the Microsoft SEAL library (FHE) and the TinyGarble2.0 framework (GC) by IntelLabs. Both implementations are evaluated under the semi-honest threat model, measuring inference output error, round-trip time, peak memory usage, communication overhead, and communication rounds. Results reveal a trade-off: modular GC offers faster execution and lower memory consumption, while FHE supports non-interactive inference.