Ilim ha’m ja’miyet № 2-1 (2026) · Саҳифаҳои 38-40

EVALUATION OF THE ROBUSTNESS OF OBJECT DETECTION MODELS AGAIUST ADVERSARIAL ATTACKS

Samatov, Boburmirzo Khamidullaevich, Yunusov, Odiljon Pozilovich, Sayidova, Nigora Komildjonovna, Саматов, Бобурмирзо Хамидуллаевич, Юнусов, Одилжон Позилович, Саидова, Нигора Комилджоновна, Samatov, Boburmirzo Xamidillo o‘g‘li, Yunusov, Odiljon Pozilovich, Sayidova, Nigora Komildjonovna

Дар манбаъ хондан

Аннотатсия

In this study, object detection systems based on convolutional neural networks were investigated, particularly the effectiveness of adversarial attacks against the YOLOv5 model. As attack methods, the Fast Gradient Sign Method (FGSM) and its improved variants (Iterative FGSM and PGD) were applied. Adversarial perturbations generated using the ResNet18 model were used to compare the object detection results of the original image and the attacked image. The results demonstrated that even a small amount of noise can significantly mislead an object detection model. Adversarial attacks represent one of the major vulnerabilities of artificial intelligence models, especially deep learning–based image recognition systems. Attacks such as FGSM and PGD modify the model input with small perturbations, forcing the model to produce incorrect classifications.

FGSMYOLOv5PGDFaster R-CNNResNet18CNNFGSMYOLOv5PGDFaster R-CNN

Манбаи метамаълумот: бойгонии OAI-PMH-и маҷалла · Sindex матни пурраро нигоҳ намедорад, ба манбаъ пайванд медиҳад.

Иқтибос гирифтан

APA 7 
Samatov, Boburmirzo Khamidullaevich, Yunusov, Odiljon Pozilovich, Sayidova, Nigora Komildjonovna, Саматов, Бобурмирзо Хамидуллаевич, Юнусов, Одилжон Позилович, Саидова, Нигора Комилджоновна, Samatov, Boburmirzo Xamidillo o‘g‘li, Yunusov, Odiljon Pozilovich & Sayidova, Nigora Komildjonovna (2026). EVALUATION OF THE ROBUSTNESS OF OBJECT DETECTION MODELS AGAIUST ADVERSARIAL ATTACKS. Ilim ha’m ja’miyet, (2-1), 38-40.
GOST R 7.0.5 
Samatov, Boburmirzo Khamidullaevich, Yunusov, Odiljon Pozilovich, Sayidova, Nigora Komildjonovna, Саматов, Бобурмирзо Хамидуллаевич, Юнусов, Одилжон Позилович, Саидова, Нигора Комилджоновна, Samatov, Boburmirzo Xamidillo o‘g‘li, Yunusov, Odiljon Pozilovich, Sayidova, Nigora Komildjonovna EVALUATION OF THE ROBUSTNESS OF OBJECT DETECTION MODELS AGAIUST ADVERSARIAL ATTACKS // Ilim ha’m ja’miyet. 2026. № 2-1. С. 38-40.
BibTeX 
@article{khamidullaevich2026,
  author  = {Samatov, Boburmirzo Khamidullaevich and Yunusov, Odiljon Pozilovich and Sayidova, Nigora Komildjonovna and Саматов, Бобурмирзо Хамидуллаевич and Юнусов, Одилжон Позилович and Саидова, Нигора Комилджоновна and Samatov, Boburmirzo Xamidillo o‘g‘li and Yunusov, Odiljon Pozilovich and Sayidova, Nigora Komildjonovna},
  title   = {EVALUATION OF THE ROBUSTNESS OF OBJECT DETECTION MODELS AGAIUST ADVERSARIAL ATTACKS},
  journal = {Ilim ha’m ja’miyet},
  year    = {2026},
  number  = {2-1},
  pages   = {38-40}
}
RIS 
TY  - JOUR
AU  - Samatov, Boburmirzo Khamidullaevich
AU  - Yunusov, Odiljon Pozilovich
AU  - Sayidova, Nigora Komildjonovna
AU  - Саматов, Бобурмирзо Хамидуллаевич
AU  - Юнусов, Одилжон Позилович
AU  - Саидова, Нигора Комилджоновна
AU  - Samatov, Boburmirzo Xamidillo o‘g‘li
AU  - Yunusov, Odiljon Pozilovich
AU  - Sayidova, Nigora Komildjonovna
TI  - EVALUATION OF THE ROBUSTNESS OF OBJECT DETECTION MODELS AGAIUST ADVERSARIAL ATTACKS
JO  - Ilim ha’m ja’miyet
PY  - 2026
IS  - 2-1
SP  - 38
EP  - 40
ER  -