7 papers
Contract And Conquer: How to Provably Compute Adversarial Examples for a Black-Box Model?
Anna Chistyakova, Mikhail Pautov
Black-box adversarial attacks are widely used as tools to test the robustness of deep neural networks against malicious perturbations of input data aimed at a specific change in th…
RandMark: On Random Watermarking of Visual Foundation Models
Anna Chistyakova, Mikhail Pautov
Being trained on large and diverse datasets, visual foundation models (VFMs) can be fine-tuned to achieve remarkable performance and efficiency in various downstream computer visio…
Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics
Alexander Gushchin, Khaled Abud, Georgii Bychkov +7
In the field of Image Quality Assessment (IQA), the adversarial robustness of the metrics poses a critical concern. This paper presents a comprehensive benchmarking study of variou…
ActiveMark: on watermarking of visual foundation models via massive activations
Anna Chistyakova, Mikhail Pautov
Being trained on large and vast datasets, visual foundation models (VFMs) can be fine-tuned for diverse downstream tasks, achieving remarkable performance and efficiency in various…
Robustness as Architecture: Designing IQA Models to Withstand Adversarial Perturbations
Igor Meleshin, Anna Chistyakova, Anastasia Antsiferova +1
Image Quality Assessment (IQA) models are increasingly relied upon to evaluate image quality in real-world systems -- from compression and enhancement to generation and streaming.…
Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods
Egor Kovalev, Georgii Bychkov, Khaled Abud +5
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…