Maxim Khrebtov

Mr. Maxim Khrebtov

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
5 November 2024 in Technologies
Verified
Journal Article
Open access
PDF file
ACAnna Chistyakova
Anna Chistyakova
AAAnastasia Antsiferova
Anastasia Antsiferova
MKMaxim Khrebtov
Maxim Khrebtov
SLSergey Lavrushkin
Sergey Lavrushkin
KAKonstantin Arkhipenko
Konstantin Arkhipenko
DTDenis Turdakov
Denis Turdakov
The adversarial robustness of image quality assessment (IQA) models to adversarial attacks is emerging as a critical issue. Adversarial training has been widely used to improve the robustness of neural networks to adversarial attacks, but little in-depth research has examined adversarial training as a way to improve IQA model robustness. This study introduces an enhanced adversarial training approach tailored to IQA models; it adjusts the perceptual quality scores of adversarial images during training to enhance the correlation between an IQA model’s quality and the subjective quality scores. We also propose a new method for comparing IQA model robustness by measuring the Integral Robustness Score; this method evaluates the IQA model resistance to a set of adversarial perturbations with different magnitudes. We used our adversarial training approach to increase the robustness of five IQA models. Additionally, we tested the robustness of adversarially trained IQA models to 16 adversarial attacks and conducted an empirical probabilistic estimation of this feature.

24 October 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
ACAnna Chistyakova
Anna Chistyakova
AAAnastasia Antsiferova
Anastasia Antsiferova
MKMaxim Khrebtov
Maxim Khrebtov
SLSergey Lavrushkin
Sergey Lavrushkin
KAKonstantin Arkhipenko
Konstantin Arkhipenko
DTDenis Turdakov
Denis Turdakov
The adversarial robustness of image quality assessment (IQA) models to adversarial attacks is emerging as a critical issue. Adversarial training has been widely used to improve the robustness of neural networks to adversarial attacks, but little in-depth research has examined adversarial training as a way to improve IQA model robustness. This study introduces an enhanced adversarial training approach tailored to IQA models; it adjusts the perceptual quality scores of adversarial images during training to enhance the correlation between an IQA model’s quality and the subjective quality scores. We also propose a new method for comparing IQA model robustness by measuring the Integral Robustness Score; this method evaluates the IQA model resistance to a set of adversarial perturbations with different magnitudes. We used our adversarial training approach to increase the robustness of five IQA models. Additionally, we tested the robustness of adversarially trained IQA models to 16 adversarial attacks and conducted an empirical probabilistic estimation of this feature. The code is available at https://github.com/wianluna/metrics_at.

30 April 2025 in Multimedia Systems
Verified
Journal Article
Closed access
PDF file
SLSergey Lavrushkin
Sergey Lavrushkin
MKMaxim Khrebtov
Maxim Khrebtov
AAAnastasia Antsiferova
Anastasia Antsiferova
GBGeorgii Bychkov
Georgii Bychkov
ASAlexey Soloviev
Alexey Soloviev
Dmitriy VatolinDmitriy Vatolin
Dmitriy Vatolin