Analyzing User-Level Privacy Attack Against Federated Learning

Mengkai Song; Zhibo Wang; Zhifei Zhang; Yang Song; Qian Wang; Ju Ren; Hairong Qi

doi:10.1109/jsac.2020.3000372

Analyzing User-Level Privacy Attack Against Federated Learning

IEEE Journal on Selected Areas in Communications ◽

10.1109/jsac.2020.3000372 ◽

2020 ◽

Vol 38 (10) ◽

pp. 2430-2444 ◽

Cited By ~ 5

Author(s):

Mengkai Song ◽

Zhibo Wang ◽

Zhifei Zhang ◽

Yang Song ◽

Qian Wang ◽

...

Keyword(s):

Privacy Attack

Download Full-text

A Practical Location Privacy Attack in Proximity Services

2013 IEEE 14th International Conference on Mobile Data Management ◽

10.1109/mdm.2013.19 ◽

2013 ◽

Cited By ~ 12

Author(s):

Sergio Mascetti ◽

Letizia Bertolaja ◽

Claudio Bettini

Keyword(s):

Location Privacy ◽

Proximity Services ◽

Privacy Attack

Download Full-text

Privacy Attack and Defense Game

Encyclopedia of Wireless Networks ◽

10.1007/978-3-319-78262-1_300506 ◽

2020 ◽

pp. 1097-1097

Keyword(s):

Privacy Attack ◽

Attack And Defense

Download Full-text

Analytical Study on Privacy Attack Models in Privacy Preserving Data Publishing

Cyber Law, Privacy, and Security ◽

10.4018/978-1-5225-8897-9.ch076 ◽

2019 ◽

pp. 1518-1538

Author(s):

Sowmyarani C. N. ◽

Dayananda P.

Keyword(s):

Private Information ◽

Background Knowledge ◽

Privacy Preserving ◽

Data Publishing ◽

Background Information ◽

Published Data ◽

Privacy Attack ◽

Privacy Preserving Data Publishing ◽

Available Information ◽

Attack Models

Privacy attack on individual records has great concern in privacy preserving data publishing. When an intruder who is interested to know the private information of particular person of his interest, will acquire background knowledge about the person. This background knowledge may be gained though publicly available information such as Voter's id or through social networks. Combining this background information with published data; intruder may get the private information causing a privacy attack of that person. There are many privacy attack models. Most popular attack models are discussed in this chapter. The study of these attack models plays a significant role towards the invention of robust Privacy preserving models.

Download Full-text