Zobrazeno 1 - 10
of 2 551
pro vyhledávání: '"Sav, A"'
Large language models (LLMs) have shown considerable success in a range of domain-specific tasks, especially after fine-tuning. However, fine-tuning with real-world data usually leads to privacy risks, particularly when the fine-tuning samples exist
Externí odkaz:
http://arxiv.org/abs/2409.11423
Training deep neural networks often requires large-scale datasets, necessitating storage and processing on cloud servers due to computational constraints. The procedures must follow strict privacy regulations in domains like healthcare. Split Learnin
Externí odkaz:
http://arxiv.org/abs/2407.08977
Autor:
Polillo, Alexia, Voineskos, Aristotle N, Foussias, George, Kidd, Sean A, Sav, Andreea, Hawley, Steve, Soklaridis, Sophie, Stergiopoulos, Vicky, Kozloff, Nicole
Publikováno v:
JMIR Mental Health, Vol 8, Iss 5, p e24567 (2021)
BackgroundBarriers to recruiting and retaining people with psychosis and their families in research are well-established, potentially biasing clinical research samples. Digital research tools, such as online platforms, mobile apps, and text messaging
Externí odkaz:
https://doaj.org/article/b661f9d70cdb4ba9a256a9f983efcaf7
In this paper, we address the problem of privacy-preserving hyperparameter (HP) tuning for cross-silo federated learning (FL). We first perform a comprehensive measurement study that benchmarks various HP strategies suitable for FL. Our benchmarks sh
Externí odkaz:
http://arxiv.org/abs/2402.16087
Autor:
Intoci, Francesco, Sav, Sinem, Pyrgelis, Apostolos, Bossuat, Jean-Philippe, Troncoso-Pastoriza, Juan Ramon, Hubaux, Jean-Pierre
Homomorphic encryption (HE), which allows computations on encrypted data, is an enabling technology for confidential cloud computing. One notable example is privacy-preserving Prediction-as-a-Service (PaaS), where machine-learning predictions are com
Externí odkaz:
http://arxiv.org/abs/2305.00690
Autor:
Sav, Sinem, Diaa, Abdulrahman, Pyrgelis, Apostolos, Bossuat, Jean-Philippe, Hubaux, Jean-Pierre
We present RHODE, a novel system that enables privacy-preserving training of and prediction on Recurrent Neural Networks (RNNs) in a cross-silo federated learning setting by relying on multiparty homomorphic encryption. RHODE preserves the confidenti
Externí odkaz:
http://arxiv.org/abs/2207.13947
Publikováno v:
Turkish Journal of Plastic Surgery, Vol 32, Iss 1, Pp 32-34 (2024)
Epithelioid angiomatous nodule (EAN) is a rare benign vascular lesion that was first reported in 2004. This article presents the case of a 29-year-old male with multiple focal EANs on his penis, a highly uncommon location for this condition. The pati
Externí odkaz:
https://doaj.org/article/1ba941f8d1474cefb4bf917159e786f3
Autor:
Modra, Lucy J., Higgins, Alisa M., Pilcher, David V., Cheung, Ada S., Carpenter, Morgan N., Bailey, Michael, Zwickl, Sav, Bellomo, Rinaldo
Publikováno v:
In Chest May 2024 165(5):1120-1128
Autor:
Sav, Sinem, Pyrgelis, Apostolos, Troncoso-Pastoriza, Juan R., Froelicher, David, Bossuat, Jean-Philippe, Sousa, Joao Sa, Hubaux, Jean-Pierre
In this paper, we address the problem of privacy-preserving training and evaluation of neural networks in an $N$-party, federated learning setting. We propose a novel system, POSEIDON, the first of its kind in the regime of privacy-preserving neural
Externí odkaz:
http://arxiv.org/abs/2009.00349
Autor:
Froelicher, David, Troncoso-Pastoriza, Juan R., Pyrgelis, Apostolos, Sav, Sinem, Sousa, Joao Sa, Bossuat, Jean-Philippe, Hubaux, Jean-Pierre
In this paper, we address the problem of privacy-preserving distributed learning and the evaluation of machine-learning models by analyzing it in the widespread MapReduce abstraction that we extend with privacy constraints. We design SPINDLE (Scalabl
Externí odkaz:
http://arxiv.org/abs/2005.09532