Results 311 to 320 of about 1,840,684 (372)
Some of the next articles are maybe not open access.
Data Mining and Knowledge Discovery, 2007
We describe two algorithms, BiBoost (Bipartite Boosting) and MultBoost (Multiparty Boosting), that allow two or more participants to construct a boosting classifier without explicitly sharing their data sets. We analyze both the computational and the security aspects of the algorithms.
Gambs, Sebastien +2 more
openaire +2 more sources
We describe two algorithms, BiBoost (Bipartite Boosting) and MultBoost (Multiparty Boosting), that allow two or more participants to construct a boosting classifier without explicitly sharing their data sets. We analyze both the computational and the security aspects of the algorithms.
Gambs, Sebastien +2 more
openaire +2 more sources
ShieldFL: Mitigating Model Poisoning Attacks in Privacy-Preserving Federated Learning
IEEE Transactions on Information Forensics and Security, 2022Privacy-Preserving Federated Learning (PPFL) is an emerging secure distributed learning paradigm that aggregates user-trained local gradients into a federated model through a cryptographic protocol.
Zhuo Ma +4 more
semanticscholar +1 more source
Privacy-preserving Cooperative Positioning
ION GNSS+, The International Technical Meeting of the Satellite Division of The Institute of Navigation, 2020We address the issue of user privacy in the context of “collaborative” positioning, wherein information is passed between and processed by multiple cooperative agents with the goal of achieving high levels of positioning accuracy. In particular, we evaluate the feasibility of applying a layer of encryption to a linear least squares (LS) algorithm for ...
Hernandez, Guillermo +2 more
openaire +1 more source
Privacy-Preserving Byzantine-Robust Federated Learning via Blockchain Systems
IEEE Transactions on Information Forensics and Security, 2022Federated learning enables clients to train a machine learning model jointly without sharing their local data. However, due to the centrality of federated learning framework and the untrustworthiness of clients, traditional federated learning solutions ...
Yinbin Miao +4 more
semanticscholar +1 more source
SPDL: A Blockchain-Enabled Secure and Privacy-Preserving Decentralized Learning System
IEEE transactions on computers, 2023Decentralized learning involves training machine learning models over remote mobile devices, edge servers, or cloud servers while keeping data localized.
Minghui Xu +5 more
semanticscholar +1 more source
Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services
IEEE Transactions on Audio, Speech, and Language Processing, 2023Parameter-Efficient Fine-Tuning (PEFT) provides a practical way for users to customize Large Language Models (LLMs) with their private data in LLM service scenarios.
Yansong Li +3 more
semanticscholar +1 more source
Econometrics with Privacy Preservation
Operations Research, 2019Summary: Many data are sensitive in areas such as finance, economics, and other social sciences. We propose an ER (encryption and recovery) algorithm that allows a central administration to do statistical inference based on the encrypted data, while still preserving each party's privacy even for a colluding majority in the presence of cyber attack.
Ning Cai, Steven Kou
openaire +3 more sources
PPFL: privacy-preserving federated learning with trusted execution environments
ACM SIGMOBILE International Conference on Mobile Systems, Applications, and Services, 2021We propose and implement a Privacy-preserving Federated Learning (PPFL) framework for mobile systems to limit privacy leakages in federated learning.
Fan Mo +5 more
semanticscholar +1 more source
Privacy-Preserving Trust Negotiations
2005Trust negotiation is a promising approach for establishing trust in open systems, where sensitive interactions may often occur between entities with no prior knowledge of each other. Although several proposals today exist of systems for the management of trust negotiations none of them addresses in a comprehensive way the problem of privacy ...
ELISA BERTINO +2 more
openaire +2 more sources
BOLT: Privacy-Preserving, Accurate and Efficient Inference for Transformers
IEEE Symposium on Security and PrivacyThe advent of transformers has brought about significant advancements in traditional machine learning tasks. However, their pervasive deployment has raised concerns about the potential leakage of sensitive information during inference.
Qi Pang +4 more
semanticscholar +1 more source