Deep Learning on Private Data

被引：0

作者：

Fasano, Andrew ^{[1
,2
]}

Leek, Tim ^{[1
]}

Dolan-Gavitt, Brendan ^{[3
]}

Bundt, Josh ^{[2
,4
]}

机构：

[1] MIT Lincoln Lab, Lexington, MA 02421 USA

[2] Northeastern Univ, Boston, MA 02115 USA

[3] NYU, New York, NY 10003 USA

[4] US Army, Cyber Inst, Washington, DC 20310 USA

来源：

IEEE SECURITY & PRIVACY | 2019年 / 17卷 / 06期

关键词：

Training; Protocols; Cryptography; Servers; Computational modeling; Data models; Logic gates;

D O I：

10.1109/MSEC.2019.2933682

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Emerging complex deep neural networks require vast amounts of data to achieve high precision. However, the information is often collected from user logs and personal data. In this article, we summarize recent cryptographic methodologies for provably privacy-preserving deep learning and inference.

引用

页码：84 / 88

页数：5

共 50 条

[31] Limits of Private Learning with Access to Public Data
Alon, Noga
Bassily, Raef
Moran, Shay
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
[32] Differentially Private Distance Learning in Categorical Data
Elena Battaglia
Simone Celano
Ruggero G. Pensa
[J]. Data Mining and Knowledge Discovery, 2021, 35 : 2050 - 2088
[33] Differentially private Bayesian learning on distributed data
Heikkila, Mikko
Lagerspetz, Eemil
Kaski, Samuel
Shimizu, Kana
Tarkoma, Sasu
Honkela, Antti
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
[34] Private data release via learning thresholds
Hardt, Moritz
Rothblum, Guy N.
Servedio, Rocco A.
[J]. Proceedings of the Annual ACM-SIAM Symposium on Discrete Algorithms, 2012, : 168 - 187
[35] Optimized Deep Learning for Enhanced Trade-off in Differentially Private Learning
Geetha, P.
Naikodi, Chandrakant
Suresh, L.
[J]. ENGINEERING TECHNOLOGY & APPLIED SCIENCE RESEARCH, 2021, 11 (01) : 6745 - 6751
[36] A deep learning approach to private data sharing of medical images using conditional generative adversarial networks (GANs)
Sun, Hanxi
Plawinski, Jason
Subramaniam, Sajanth
Jamaludin, Amir
Kadir, Timor
Readie, Aimee
Ligozio, Gregory
Ohlssen, David I.
Baillie, Mark
Coroller, Thibaud
[J]. PLOS ONE, 2023, 18 (07):
[37] Differentially-Private Deep Learning from an Optimization Perspective
Xiang, Liyao
Yang, Jingbo
Li, Baochun
[J]. IEEE CONFERENCE ON COMPUTER COMMUNICATIONS (IEEE INFOCOM 2019), 2019, : 559 - 567
[38] Terahertz Metamaterial Intelligent Identification by Private Preserving Deep Learning
Liu, Feifei
Zhang, Weihao
Sun, Yu
Liu, Jianwei
Wu, Xiaojun
[J]. 2020 45TH INTERNATIONAL CONFERENCE ON INFRARED, MILLIMETER, AND TERAHERTZ WAVES (IRMMW-THZ), 2020,
[39] An optimal (ε, δ)-differentially private learning of distributed deep fuzzy models
Kumar, Mohit
Rossbory, Michael
Moser, Bernhard A.
Freudenthaler, Bernhard
[J]. INFORMATION SCIENCES, 2021, 546 : 87 - 120
[40] Deep Efficient Private Neighbor Generation for Subgraph Federated Learning
Zhang, Ke
Sun, Lichao
Ding, Bolin
Yiu, Siu Ming
Yang, Carl
[J]. PROCEEDINGS OF THE 2024 SIAM INTERNATIONAL CONFERENCE ON DATA MINING, SDM, 2024, : 806 - 814

← 1 2 3 4 5 →