Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Burkhalter, Lukas"'
As increasingly more sensitive data is being collected to gain valuable insights, the need to natively integrate privacy controls in data analytics frameworks is growing in importance. Today, privacy controls are enforced by data curators with full a
Externí odkaz:
http://arxiv.org/abs/2107.03726
Even though recent years have seen many attacks exposing severe vulnerabilities in Federated Learning (FL), a holistic understanding of what enables these attacks and how they can be mitigated effectively is still lacking. In this work, we demystify
Externí odkaz:
http://arxiv.org/abs/2107.03311
A growing number of devices and services collect detailed time series data that is stored in the cloud. Protecting the confidentiality of this vast and continuously generated data is an acute need for many applications in this space. At the same time
Externí odkaz:
http://arxiv.org/abs/1811.03457
Publikováno v:
USENIX Security 2020
This paper presents Droplet, a decentralized data access control service. Droplet enables data owners to securely and selectively share their encrypted data while guaranteeing data confidentiality in the presence of unauthorized parties and compromis
Externí odkaz:
http://arxiv.org/abs/1806.02057
Today the cloud plays a central role in storing, processing, and distributing data. Despite contributing to the rapid development of IoT applications, the current IoT cloud-centric architecture has led into a myriad of isolated data silos that hinder
Externí odkaz:
http://arxiv.org/abs/1705.08230
Autor:
Burkhalter, Lukas
In recent years we have seen unprecedented growth in networked devices and services that collect increasingly detailed information about individuals. This trend of large-scale data collection prompts various important challenges, including ensuring t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0beb71cc7735b414f3de107546b3af6c
https://hdl.handle.net/20.500.11850/594164
https://hdl.handle.net/20.500.11850/594164
Autor:
Jiang, Jiawei, Burkhalter, Lukas, Fu, Fangcheng, Ding, Bolin, Du, Bo, Hithnawi, Anwar, Li, Bo, Zhang, Ce
Publikováno v:
Advances in Neural Information Processing Systems 35
Vertical Federated Learning (VFL), that trains federated models over vertically partitioned data, has emerged as an important learning paradigm. However, existing VFL methods are facing two challenges: (1) scalability when # participants grows to eve
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______150::49c9b2e165f56ecffc1eee97ae17db9d
https://hdl.handle.net/20.500.11850/590694
https://hdl.handle.net/20.500.11850/590694
Publikováno v:
Proceedings of the 17th USENIX Symposium on Networked Systems Design and Implementation
A growing number of devices and services collect detailed time series data that is stored in the cloud. Protecting the confidentiality of this vast and continuously generated data is an acute need for many applications in this space. At the same time
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2c57e9bfeeafa7b694c1fdf7c69b5ea2
Publikováno v:
Proceedings of the 29th USENIX Security Symposium
Proceedings of the 29th USENIX Security Symposium
ISBN:978-1-939133-17-5
ISBN:978-1-939133-17-5
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::57549cd6198d4e5ab963a7d2cebf26fc