4 citations · 7 across the 11 of their papers we have counts for
12 papers
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…
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…
Robustness Tokens: Towards Adversarial Robustness of Transformers
Brian Pulfer, Yury Belousov, Slava Voloshynovskiy
Recently, large pre-trained foundation models have become widely adopted by machine learning practitioners for a multitude of tasks. Given that such models are publicly available,…
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…
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.…
Assessing the Viability of Synthetic Physical Copy Detection Patterns on Different Imaging Systems
Roman Chaban, Brian Pulfer, Slava Voloshynovskiy
This paper explores the potential of synthetic physical Copy Detection Patterns (CDP) to improve the robustness of anti-counterfeiting systems. By leveraging synthetic physical CDP…
Mathematical model of printing-imaging channel for blind detection of fake copy detection patterns
Joakim Tutt, Olga Taran, Roman Chaban +4
Nowadays, copy detection patterns (CDP) appear as a very promising anti-counterfeiting technology for physical object protection. However, the advent of deep learning as a powerful…
Solving the Weather4cast Challenge via Visual Transformers for 3D Images
Yury Belousov, Sergey Polezhaev, Brian Pulfer
Accurately forecasting the weather is an important task, as many real-world processes and decisions depend on future meteorological conditions. The NeurIPS 2022 challenge entitled…
Digital twins of physical printing-imaging channel
Yury Belousov, Brian Pulfer, Roman Chaban +4
In this paper, we address the problem of modeling a printing-imaging channel built on a machine learning approach a.k.a. digital twin for anti-counterfeiting applications based on…
Printing variability of copy detection patterns
Roman Chaban, Olga Taran, Joakim Tutt +4
Copy detection pattern (CDP) is a novel solution for products' protection against counterfeiting, which gains its popularity in recent years. CDP attracts the anti-counterfeiting i…
Anomaly localization for copy detection patterns through print estimations
Brian Pulfer, Yury Belousov, Joakim Tutt +4
Copy detection patterns (CDP) are recent technologies for protecting products from counterfeiting. However, in contrast to traditional copy fakes, deep learning-based fakes have sh…
Authentication of Copy Detection Patterns under Machine Learning Attacks: A Supervised Approach
Brian Pulfer, Roman Chaban, Yury Belousov +4
Copy detection patterns (CDP) are an attractive technology that allows manufacturers to defend their products against counterfeiting. The main assumption behind the protection mech…