11 citations · 20 across the 9 of their papers we have counts for
9 papers
Synchronization-Free Algebraic Fingerprints for Large Language Models: From Autoregressive to Diffusion Models
Jaroslaw Janas, Josef Pieprzyk, Pawel Morawiecki
Large Language Models (LLMs) have created an urgent need for reliable watermarking methods that enable attribution of generated text while remaining robust to editing and paraphras…
LLM-Text Watermarking based on Lagrange Interpolation
Jarosław Janas, Paweł Morawiecki, Josef Pieprzyk
The rapid advancement of LLMs (Large Language Models) has established them as a foundational technology for many AI and ML-powered human computer interactions. A critical challenge…
Can Models Help Us Create Better Models? Evaluating LLMs as Data Scientists
Michał Pietruszka, Łukasz Borchmann, Aleksander Jędrosz +1
We present a benchmark for large language models designed to tackle one of the most knowledge-intensive tasks in data science: writing feature engineering code, which requires doma…
Towards More Realistic Membership Inference Attacks on Large Diffusion Models
Jan Dubiński, Antoni Kowalczuk, Stanisław Pawlak +3
Generative diffusion models, including Stable Diffusion and Midjourney, can generate visually appealing, diverse, and high-resolution images for various applications. These models…
Compression Optimality of Asymmetric Numeral Systems
Josef Pieprzyk, Jarek Duda, Marcin Pawlowski +3
Compression also known as entropy coding has a rich and long history. However, a recent explosion of multimedia Internet applications (such as teleconferencing and video streaming…
Hebbian Continual Representation Learning
Paweł Morawiecki, Andrii Krutsylo, Maciej Wołczyk +1
Continual Learning aims to bring machine learning into a more realistic scenario, where tasks are learned sequentially and the i.i.d. assumption is not preserved. Although this set…
Continual Learning with Guarantees via Weight Interval Constraints
Maciej Wołczyk, Karol J. Piczak, Bartosz Wójcik +5
We introduce a new training paradigm that enforces interval constraints on neural network parameter space to control forgetting. Contemporary Continual Learning (CL) methods focus…
Adversarial Examples Detection and Analysis with Layer-wise Autoencoders
Bartosz Wójcik, Paweł Morawiecki, Marek Śmieja +3
We present a mechanism for detecting adversarial examples based on data representations taken from the hidden layers of the target network. For this purpose, we train individual au…
Fast and Stable Interval Bounds Propagation for Training Verifiably Robust Models
Paweł Morawiecki, Przemysław Spurek, Marek Śmieja +1
We present an efficient technique, which allows to train classification networks which are verifiably robust against norm-bounded adversarial attacks. This framework is built upon…