3 papers
cs.CR2025
Watermark Overwriting Attack on StegaStamp algorithm
I. F. Serzhenko, L. A. Khaertdinova, M. A. Pautov +1
This paper presents an attack method on the StegaStamp watermarking algorithm that completely removes watermarks from an image with minimal quality loss, developed as part of the N…
eess.IV2024
Stochastic BIQA: Median Randomized Smoothing for Certified Blind Image Quality Assessment
Ekaterina Shumitskaya, Mikhail Pautov, Dmitriy Vatolin +1
Most modern No-Reference Image-Quality Assessment (NR-IQA) metrics are based on neural networks vulnerable to adversarial attacks. Attacks on such metrics lead to incorrect image/v…
cs.LG2024
Model Mimic Attack: Knowledge Distillation for Provably Transferable Adversarial Examples
Kirill Lukyanov, Andrew Perminov, Denis Turdakov +1
The vulnerability of artificial neural networks to adversarial perturbations in the black-box setting is widely studied in the literature. The majority of attack methods to constru…