Khaled Abud
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Khaled Abud has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Dmitriy Vatolin
Lomonosov Moscow State University, Moscow, Russia
5 shared publications - Sergey Lavrushkin
MSU Institute for Artificial Intelligence, Moscow, Russian Federation
4 shared publications - Anastasia Antsiferova
AI Center, Lomonosov Moscow State University, Lomonosovsky ave 27b1, Moscow 119991, Russia
3 shared publications - Aleksandr Gushchin
Lomonosov Moscow State University
2 shared publications - Aleksandr Akimenkov
Trusted AI Research Center RAS, Moscow, Russian Federation
1 shared publication - Aleksey Yur'Evich Yakushev
Trusted AI Research Center RAS, Moscow, Russian Federation
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7-16
WARP: A Unified Benchmark for Invisible Image Watermarking - Robustness and Protection Against Attacks
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7-16
Open AccessWARP: A Unified Benchmark for Invisible Image Watermarking - Robustness and Protection Against Attacks
- 10 September 2026
- Published by Springer Nature
- p. 188-206
FreeFlow: A Bias-Free Hierarchical Transformer for Optical Flow Estimation
- 10 September 2026
- Published by Springer Nature
- p. 188-206
FreeFlow: A Bias-Free Hierarchical Transformer for Optical Flow Estimation
- Open Access
- 25 June 2025
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 9 (7) , 166
Evaluating Adversarial Robustness of No-Reference Image and Video Quality Assessment Models with Frequency-Masked Gradient Orthogonalization Adversarial Attack
Neural-network-based models have made considerable progress in many computer vision areas over recent years. However, many works have exposed their vulnerability to malicious input data manipulation—that is, to adversarial attacks. Although many recent works have thoroughly examined the adversarial robustness of classifiers, the robustness of Image Quality Assessment (IQA) methods remains understudied. This paper addresses this gap by proposing FM-GOAT (Frequency-Masked Gradient Orthogonalization Attack), a novel white box adversarial method tailored for no-reference IQA models. Using a novel gradient orthogonalization technique, FM-GOAT uniquely optimizes adversarial perturbations against multiple perceptual constraints to minimize visibility, moving beyond traditional -norm bounds. We evaluate FM-GOAT on seven state-of-the-art NR-IQA models across three image and video datasets, revealing significant vulnerability to the proposed attack. Furthermore, we examine the applicability of adversarial purification methods to the IQA task, as well as their efficiency in mitigating white box adversarial attacks. By studying the activations from models’ intermediate layers, we explore their behavioral patterns in adversarial scenarios and discover valuable insights that may lead to better adversarial detection.- 25 June 2025
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 9 (7) , 166
Open AccessEvaluating Adversarial Robustness of No-Reference Image and Video Quality Assessment Models with Frequency-Masked Gradient Orthogonalization Adversarial Attack
Neural-network-based models have made considerable progress in many computer vision areas over recent years. However, many works have exposed their vulnerability to malicious input data manipulation—that is, to adversarial attacks. Although many recent works have thoroughly examined the adversarial robustness of classifiers, the robustness of Image Quality Assessment (IQA) methods remains understudied. This paper addresses this gap by proposing FM-GOAT (Frequency-Masked Gradient Orthogonalization Attack), a novel white box adversarial method tailored for no-reference IQA models. Using a novel gradient orthogonalization technique, FM-GOAT uniquely optimizes adversarial perturbations against multiple perceptual constraints to minimize visibility, moving beyond traditional -norm bounds. We evaluate FM-GOAT on seven state-of-the-art NR-IQA models across three image and video datasets, revealing significant vulnerability to the proposed attack. Furthermore, we examine the applicability of adversarial purification methods to the IQA task, as well as their efficiency in mitigating white box adversarial attacks. By studying the activations from models’ intermediate layers, we explore their behavioral patterns in adversarial scenarios and discover valuable insights that may lead to better adversarial detection. - Open Access
Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods
Adversarial robustness of neural networks is an increasingly important area of research, combining studies on computer vision models, large language models (LLMs), and others. With the release of JPEG AI - the first standard for end-to-end neural image compression (NIC) methods - the question of its robustness has become critically significant. JPEG AI is among the first international, real-world applications of neural-network-based models to be embedded in consumer devices. However, research on NIC robustness has been limited to open-source codecs and a narrow range of attacks. This paper proposes a new methodology for measuring NIC robustness to adversarial attacks. We present the first large-scale evaluation of JPEG AI's robustness, comparing it with other NIC models. Our evaluation results and code are publicly available online (link is hidden for a blind review).
Open AccessExploring adversarial robustness of JPEG AI: methodology, comparison and new methods
Adversarial robustness of neural networks is an increasingly important area of research, combining studies on computer vision models, large language models (LLMs), and others. With the release of JPEG AI - the first standard for end-to-end neural image compression (NIC) methods - the question of its robustness has become critically significant. JPEG AI is among the first international, real-world applications of neural-network-based models to be embedded in consumer devices. However, research on NIC robustness has been limited to open-source codecs and a narrow range of attacks. This paper proposes a new methodology for measuring NIC robustness to adversarial attacks. We present the first large-scale evaluation of JPEG AI's robustness, comparing it with other NIC models. Our evaluation results and code are publicly available online (link is hidden for a blind review).
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (2) , 700-708
Comparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attacks
Nowadays, neural-network-based image- and video-quality metrics perform better than traditional methods. However, they also became more vulnerable to adversarial attacks that increase metrics' scores without improving visual quality. The existing benchmarks of quality metrics compare their performance in terms of correlation with subjective quality and calculation time. Nonetheless, the adversarial robustness of image-quality metrics is also an area worth researching. This paper analyses modern metrics' robustness to different adversarial attacks. We adapted adversarial attacks from computer vision tasks and compared attacks' efficiency against 15 no-reference image- and video-quality metrics. Some metrics showed high resistance to adversarial attacks, which makes their usage in benchmarks safer than vulnerable metrics. The benchmark accepts submissions of new metrics for researchers who want to make their metrics more robust to attacks or to find such metrics for their needs. The latest results can be found online: https://videoprocessing.ai/benchmarks/metrics-robustness.html.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (2) , 700-708
Open AccessComparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attacks
Nowadays, neural-network-based image- and video-quality metrics perform better than traditional methods. However, they also became more vulnerable to adversarial attacks that increase metrics' scores without improving visual quality. The existing benchmarks of quality metrics compare their performance in terms of correlation with subjective quality and calculation time. Nonetheless, the adversarial robustness of image-quality metrics is also an area worth researching. This paper analyses modern metrics' robustness to different adversarial attacks. We adapted adversarial attacks from computer vision tasks and compared attacks' efficiency against 15 no-reference image- and video-quality metrics. Some metrics showed high resistance to adversarial attacks, which makes their usage in benchmarks safer than vulnerable metrics. The benchmark accepts submissions of new metrics for researchers who want to make their metrics more robust to attacks or to find such metrics for their needs. The latest results can be found online: https://videoprocessing.ai/benchmarks/metrics-robustness.html.