Results 21 to 30 of about 1,813,618 (360)

Privacy preserving data visualizations

open access: yesEPJ Data Science, 2021
Data visualizations are a valuable tool used during both statistical analysis and the interpretation of results as they graphically reveal useful information about the structure, properties and relationships between variables, which may otherwise be ...
Demetris Avraam   +7 more
doaj   +1 more source

FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System [PDF]

open access: yesarXiv.org, 2023
Federated Learning trains machine learning models on distributed devices by aggregating local model updates instead of local data. However, privacy concerns arise as the aggregated local models on the server may reveal sensitive personal information by ...
Weizhao Jin   +6 more
semanticscholar   +1 more source

Personalized privacy preservation [PDF]

open access: yesProceedings of the 2006 ACM SIGMOD international conference on Management of data, 2006
We study generalization for preserving privacy in publication of sensitive data. The existing methods focus on a universal approach that exerts the same amount of preservation for all persons, with-out catering for their concrete needs. The consequence is that we may be offering insufficient protection to a subset of people, while applying excessive ...
Xiaokui Xiao, Yufei Tao 0001
openaire   +1 more source

CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU [PDF]

open access: yesIEEE Symposium on Security and Privacy, 2021
We introduce CryptGPU, a system for privacy-preserving machine learning that implements all operations on the GPU (graphics processing unit). Just as GPUs played a pivotal role in the success of modern deep learning, they are also essential for realizing
Sijun Tan   +3 more
semanticscholar   +1 more source

Privacy‐preserving federated learning based on multi‐key homomorphic encryption [PDF]

open access: yesInternational Journal of Intelligent Systems, 2021
With the advance of machine learning and the Internet of Things (IoT), security and privacy have become critical concerns in mobile services and networks. Transferring data to a central unit violates the privacy of sensitive data.
Jing Ma, Si-Ahmed Naas, S. Sigg, X. Lyu
semanticscholar   +1 more source

Privacy-Preserving Bin-Packing With Differential Privacy

open access: yesIEEE Open Journal of Signal Processing, 2022
With the emerging of e-commerce, package theft is at a high level: It is reported that 1.7 million packages are stolen or lost every day in the U.S. in 2020, which costs $25 million every day for the lost packages and the service.
Tianyu Li   +2 more
doaj   +1 more source

Privacy-Preserving Blockchain Technologies

open access: yesSensors, 2023
The main characteristics of blockchains, such as security and traceability, have enabled their use in many distinct scenarios, such as the rise of new cryptocurrencies and decentralized applications (dApps).
Dalton Cézane Gomes Valadares   +4 more
doaj   +1 more source

RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response [PDF]

open access: yesConference on Computer and Communications Security, 2014
Randomized Aggregatable Privacy-Preserving Ordinal Response, or RAPPOR, is a technology for crowdsourcing statistics from end-user client software, anonymously, with strong privacy guarantees.
Ú. Erlingsson, A. Korolova, Vasyl Pihur
semanticscholar   +1 more source

Privacy-preserving artificial intelligence in healthcare: Techniques and applications

open access: yesComput. Biol. Medicine, 2023
There has been an increasing interest in translating artificial intelligence (AI) research into clinically-validated applications to improve the performance, capacity, and efficacy of healthcare services.
N. Khalid   +4 more
semanticscholar   +1 more source

Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation [PDF]

open access: yesInternational Conference on Learning Representations, 2023
We study the problem of in-context learning (ICL) with large language models (LLMs) on private datasets. This scenario poses privacy risks, as LLMs may leak or regurgitate the private examples demonstrated in the prompt. We propose a novel algorithm that
Xinyu Tang   +8 more
semanticscholar   +1 more source

Home - About - Disclaimer - Privacy