10 citations · 35 across the 19 of their papers we have counts for
20 papers
NAWE: Digital Watermarking with Neural-Assisted Watermark Extraction
Roman Chaban, Vitaliy Kinakh, Lilian Rouzaire +1
NAWE (Neural-Assisted Watermark Extraction) combines an explicit signal-processing watermarking construction with a pretrained neural host predictor. A periodic, perceptually maske…
Learning Radio Astronomical Representations with LeJEPA and Very Small Models
Erica Lastufka, Mariia Drozdova, Vitaliy Kinakh +4
Representations learned by vision foundation models pretrained on natural images have been shown to be useful for out-of-domain astronomical images. Performance on scientific downs…
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…
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…
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…
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…
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…
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…
Tabular Data Generation using Binary Diffusion
Vitaliy Kinakh, Slava Voloshynovskiy
Generating synthetic tabular data is critical in machine learning, especially when real data is limited or sensitive. Traditional generative models often face challenges due to the…
Semi-Supervised Fine-Tuning of Vision Foundation Models with Content-Style Decomposition
Mariia Drozdova, Vitaliy Kinakh, Yury Belousov +2
In this paper, we present a semi-supervised fine-tuning approach designed to improve the performance of pre-trained foundation models on downstream tasks with limited labeled data.…
Evaluation of Security of ML-based Watermarking: Copy and Removal Attacks
Vitaliy Kinakh, Brian Pulfer, Yury Belousov +3
The vast amounts of digital content captured from the real world or AI-generated media necessitate methods for copyright protection, traceability, or data provenance verification.…
Self-Supervised Learning on MeerKAT Wide-Field Continuum Images
Erica Lastufka, Omkar Bait, Olga Taran +8
Self-supervised learning (SSL) applied to natural images has demonstrated a remarkable ability to learn meaningful, low-dimension representations without labels, resulting in model…
Radio-astronomical Image Reconstruction with Conditional Denoising Diffusion Model
Mariia Drozdova, Vitaliy Kinakh, Omkar Bait +6
Reconstructing sky models from dirty radio images for accurate source localization and flux estimation is crucial for studying galaxy evolution at high redshift, especially in deep…
TURBO: The Swiss Knife of Auto-Encoders
Guillaume Quétant, Yury Belousov, Vitaliy Kinakh +1
We present a novel information-theoretic framework, termed as TURBO, designed to systematically analyse and generalise auto-encoding methods. We start by examining the principles o…
Stochastic Digital Twin for Copy Detection Patterns
Yury Belousov, Olga Taran, Vitaliy Kinakh +1
Copy detection patterns (CDP) present an efficient technique for product protection against counterfeiting. However, the complexity of studying CDP production variability often res…
MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation
Vitaliy Kinakh, Mariia Drozdova, Slava Voloshynovskiy
We present a new method of self-supervised learning and knowledge distillation based on the multi-views and multi-representations (MV-MR). The MV-MR is based on the maximization of…
Turbo-Sim: a generalised generative model with a physical latent space
Guillaume Quétant, Mariia Drozdova, Vitaliy Kinakh +2
We present Turbo-Sim, a generalised autoencoder framework derived from principles of information theory that can be used as a generative model. By maximising the mutual information…
Information-theoretic stochastic contrastive conditional GAN: InfoSCC-GAN
Vitaliy Kinakh, Mariia Drozdova, Guillaume Quétant +2
Conditional generation is a subclass of generative problems where the output of the generation is conditioned by the attribute information. In this paper, we present a stochastic c…
Generation of data on discontinuous manifolds via continuous stochastic non-invertible networks
Mariia Drozdova, Vitaliy Kinakh, Guillaume Quétant +2
The generation of discontinuous distributions is a difficult task for most known frameworks such as generative autoencoders and generative adversarial networks. Generative non-inve…
ScatSimCLR: self-supervised contrastive learning with pretext task regularization for small-scale datasets
Vitaliy Kinakh, Olga Taran, Svyatoslav Voloshynovskiy
In this paper, we consider a problem of self-supervised learning for small-scale datasets based on contrastive loss between multiple views of the data, which demonstrates the state…