Jan Dubiński

5 papers · 2023–2026 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) 🐣 Hot Topic Early Bird

Venues

AAAI (1) CVPR (1) ICML (1) NeurIPS (1) WACV (1)

Top co-authors

Adam Dziedzic (4) Franziska Boenisch (4) Antoni Kowalczuk (3) Tomasz Trzcinski (2) Stanisław Pawlak (2) Marcin Podhajski (1) Agnieszka Pręgowska (1) Przemyslaw Rokita (1) Paweł Morawiecki (1) Tomasz Paweł Michalak (1)

Research topics

Deep Learning (4) Machine Learning (4) Application Areas (4) Models (3) Artificial Intelligence (2) Core AI (2) Computer Science (1) Computer Vision (1) Security & Privacy (1) Applications (1) Architectures (1) Generation (1) Learning Types (1) Optimization & Theory (1) Privacy (1)

Keywords

diffusion model (3) membership inference (3) copyright protection (2) dataset inference (2) membership inference attack (2) adversarial attack (1) generative model (1) information leakage (1) model stealing (1) model extraction (1) copyright infringement (1) graph neural network (1) active defense (1) encoder protection (1) image autoregressive models (1) representation learning (1) training data points (1) privacy attack (1) embedding space (1) intellectual property (1)

Papers

On Stealing Graph Neural Network Models AAAI 2026 CDI: Copyrighted Data Identification in Diffusion Models CVPR 2025 Privacy Attacks on Image AutoRegressive Models ICML 2025 Towards More Realistic Membership Inference Attacks on Large Diffusion Models WACV 2024 Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders NeurIPS 2023