Imperial College London
Portrait Picture

Professor Hamed Haddadi

Faculty of Engineering, Department of Computing

Professor of Human-Centred Systems
 
 
 
//

Contact

 

h.haddadi Website

 
 
//

Location

 

2Translation & Innovation Hub BuildingWhite City Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Osia:2020:10.1109/TKDE.2018.2878698,
author = {Osia, SA and Taheri, A and Shamsabadi, AS and Katevas, K and Haddadi, H and Rabiee, HR},
doi = {10.1109/TKDE.2018.2878698},
journal = {IEEE Transactions on Knowledge and Data Engineering},
pages = {54--66},
title = {Deep Private-Feature Extraction},
url = {http://dx.doi.org/10.1109/TKDE.2018.2878698},
volume = {32},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - We present and evaluate Deep Private-Feature Extractor (DPFE), a deep model which is trained and evaluated based on information theoretic constraints. Using the selective exchange of information between a user's device and a service provider, DPFE enables the user to prevent certain sensitive information from being shared with a service provider, while allowing them to extract approved information using their model. We introduce and utilize the log-rank privacy, a novel measure to assess the effectiveness of DPFE in removing sensitive information and compare different models based on their accuracy-privacy trade-off. We then implement and evaluate the performance of DPFEon smartphones to understand its complexity, resource demands, and efficiency trade-offs. Our results on benchmark image datasets demonstrate that under moderate resource utilization, DPFE can achieve high accuracy for primary tasks while preserving the privacy of sensitive information.
AU  - Osia,SA
AU  - Taheri,A
AU  - Shamsabadi,AS
AU  - Katevas,K
AU  - Haddadi,H
AU  - Rabiee,HR
DO  - 10.1109/TKDE.2018.2878698
EP  - 66
PY  - 2020///
SN  - 1041-4347
SP  - 54
TI  - Deep Private-Feature Extraction
T2  - IEEE Transactions on Knowledge and Data Engineering
UR  - http://dx.doi.org/10.1109/TKDE.2018.2878698
UR  - http://arxiv.org/abs/1802.03151v2
UR  - https://ieeexplore.ieee.org/document/8515092
UR  - http://hdl.handle.net/10044/1/57311
VL  - 32
ER  -
Download