activity
20242026
collaborators

12 papers

cs.CV2026

Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Floyd-Steinberg Dithering

Yury Belousov, Brian Pulfer, Vitaliy Kinakh +1

Vision foundation models are widely used as frozen backbones across many downstream tasks, making them a single point of failure under adversarial attack. We study multi-level Floy…

astro-ph.IM2025

Radio Astronomy in the Era of Vision-Language Models: Prompt Sensitivity and Adaptation

Mariia Drozdova, Erica Lastufka, Vitaliy Kinakh +3

Vision-Language Models (VLMs), such as recent Qwen and Gemini models, are positioned as general-purpose AI systems capable of reasoning across domains. Yet their capabilities in sc…

cs.CV2025

Binary Diffusion Probabilistic Model

Vitaliy Kinakh, Slava Voloshynovskiy

We propose the Binary Diffusion Probabilistic Model (BDPM), a generative framework specifically designed for data representations in binary form. Conventional denoising diffusion p…

cs.LG2025

Beyond Classification: Evaluating Diffusion Denoised Smoothing for Security-Utility Trade off

Yury Belousov, Brian Pulfer, Vitaliy Kinakh +1

While foundation models demonstrate impressive performance across various tasks, they remain vulnerable to adversarial inputs. Current research explores various approaches to enhan…

astro-ph.SR2025

Enhancing Image Resolution of Solar Magnetograms: A Latent Diffusion Model Approach

Francesco Pio Ramunno, Paolo Massa, Vitaliy Kinakh +3

The spatial properties of the solar magnetic field are crucial to decoding the physical processes in the solar interior and their interplanetary effects. However, observations from…

cs.CV2025

Task-Agnostic Attacks Against Vision Foundation Models

Brian Pulfer, Yury Belousov, Vitaliy Kinakh +2

The study of security in machine learning mainly focuses on downstream task-specific attacks, where the adversarial example is obtained by optimizing a loss function specific to th…