Zobrazeno 1 - 10
of 54
pro vyhledávání: '"Dziedzic, Adam"'
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
Graph Neural Networks (GNNs) are recognized as potent tools for processing real-world data organized in graph structures. Especially inductive GNNs, which enable the processing of graph-structured data without relying on predefined graph structures,
Externí odkaz:
http://arxiv.org/abs/2405.12295
Autor:
Fang, Congyu, Dziedzic, Adam, Zhang, Lin, Oliva, Laura, Verma, Amol, Razak, Fahad, Papernot, Nicolas, Wang, Bo
Publikováno v:
eBioMedicine, vol. 101, p. 105006, 2024
Machine Learning (ML) has demonstrated its great potential on medical data analysis. Large datasets collected from diverse sources and settings are essential for ML models in healthcare to achieve better accuracy and generalizability. Sharing data ac
Externí odkaz:
http://arxiv.org/abs/2402.00205
Autor:
Wang, Wenhao, Kaleem, Muhammad Ahmad, Dziedzic, Adam, Backes, Michael, Papernot, Nicolas, Boenisch, Franziska
Self-supervised learning (SSL) has recently received significant attention due to its ability to train high-performance encoders purely on unlabeled data-often scraped from the internet. This data can still be sensitive and empirical evidence suggest
Externí odkaz:
http://arxiv.org/abs/2401.12233
Autor:
Franzese, Olive, Dziedzic, Adam, Choquette-Choo, Christopher A., Thomas, Mark R., Kaleem, Muhammad Ahmad, Rabanser, Stephan, Fang, Congyu, Jha, Somesh, Papernot, Nicolas, Wang, Xiao
Collaborative machine learning (ML) is widely used to enable institutions to learn better models from distributed data. While collaborative approaches to learning intuitively protect user data, they remain vulnerable to either the server, the clients
Externí odkaz:
http://arxiv.org/abs/2310.16678
Machine Learning as a Service (MLaaS) APIs provide ready-to-use and high-utility encoders that generate vector representations for given inputs. Since these encoders are very costly to train, they become lucrative targets for model stealing attacks d
Externí odkaz:
http://arxiv.org/abs/2310.08571
Large language models (LLMs) are excellent in-context learners. However, the sensitivity of data contained in prompts raises privacy concerns. Our work first shows that these concerns are valid: we instantiate a simple but highly effective membership
Externí odkaz:
http://arxiv.org/abs/2305.15594