Zobrazeno 1 - 10
of 13 375
pro vyhledávání: '"A. Dziedzic"'
Diffusion Models (DMs) benefit from large and diverse datasets for their training. Since this data is often scraped from the Internet without permission from the data owners, this raises concerns about copyright and intellectual property protections.
Externí odkaz:
http://arxiv.org/abs/2411.12858
Large language models (LLMs) are excellent few-shot learners. They can perform a wide variety of tasks purely based on natural language prompts provided to them. These prompts contain data of a specific downstream task -- often the private dataset of
Externí odkaz:
http://arxiv.org/abs/2411.10512
Autor:
Hanke, Vincent, Blanchard, Tom, Boenisch, Franziska, Olatunji, Iyiola Emmanuel, Backes, Michael, Dziedzic, Adam
While open Large Language Models (LLMs) have made significant progress, they still fall short of matching the performance of their closed, proprietary counterparts, making the latter attractive even for the use on highly private data. Recently, vario
Externí odkaz:
http://arxiv.org/abs/2411.05818
Recent work on studying memorization in self-supervised learning (SSL) suggests that even though SSL encoders are trained on millions of images, they still memorize individual data points. While effort has been put into characterizing the memorized d
Externí odkaz:
http://arxiv.org/abs/2409.19069
Autor:
Kowalczuk, Antoni, Dubiński, Jan, Ghomi, Atiyeh Ashari, Sui, Yi, Stein, George, Wu, Jiapeng, Cresswell, Jesse C., Boenisch, Franziska, Dziedzic, Adam
Large-scale vision models have become integral in many applications due to their unprecedented performance and versatility across downstream tasks. However, the robustness of these foundation models has primarily been explored for a single task, name
Externí odkaz:
http://arxiv.org/abs/2407.12588
Machine learning (ML) models have been shown to leak private information from their training datasets. Differential Privacy (DP), typically implemented through the differential private stochastic gradient descent algorithm (DP-SGD), has become the st
Externí odkaz:
http://arxiv.org/abs/2406.08039
The proliferation of large language models (LLMs) in the real world has come with a rise in copyright cases against companies for training their models on unlicensed data from the internet. Recent works have presented methods to identify if individua
Externí odkaz:
http://arxiv.org/abs/2406.06443
Autor:
Wang, Yihan, Lu, Yiwei, Zhang, Guojun, Boenisch, Franziska, Dziedzic, Adam, Yu, Yaoliang, Gao, Xiao-Shan
Machine unlearning provides viable solutions to revoke the effect of certain training data on pre-trained model parameters. Existing approaches provide unlearning recipes for classification and generative models. However, a category of important mach
Externí odkaz:
http://arxiv.org/abs/2406.03603
Autor:
Hintersdorf, Dominik, Struppek, Lukas, Kersting, Kristian, Dziedzic, Adam, Boenisch, Franziska
Diffusion models (DMs) produce very detailed and high-quality images. Their power results from extensive training on large amounts of data, usually scraped from the internet without proper attribution or consent from content creators. Unfortunately,
Externí odkaz:
http://arxiv.org/abs/2406.02366
Autor:
Podhajski, Marcin, Dubiński, Jan, Boenisch, Franziska, Dziedzic, Adam, Pregowska, Agnieszka, Michalak, Tomasz P.
Graph Neural Networks (GNNs) are recognized as potent tools for processing real-world data organized in graph structures. Especially inductive GNNs, which allow for the processing of graph-structured data without relying on predefined graph structure
Externí odkaz:
http://arxiv.org/abs/2405.12295