Imperial College London
Portrait Picture

Professor Emil Lupu

Faculty of Engineering, Department of Computing

Professor of Computer Systems
 
 
 
//

Contact

 

e.c.lupu Website

 
 
//

Location

 

564Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Collinge:2019,
author = {Collinge, G and Lupu, E and Munoz, Gonzalez L},
publisher = {ESANN},
title = {Defending against Poisoning Attacks in Online Learning Settings},
url = {http://hdl.handle.net/10044/1/70348},
year = {2019}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Machine learning systems are vulnerable to data poisoning, acoordinated attack where a fraction of the training dataset is manipulatedby an attacker to subvert learning. In this paper we first formulate an optimal attack strategy against online learning classifiers to assess worst-casescenarios. We also propose two defence mechanisms to mitigate the effectof online poisoning attacks by analysing the impact of the data points inthe classifier and by means of an adaptive combination of machine learning classifiers with different learning rates. Our experimental evaluationsupports the usefulness of our proposed defences to mitigate the effect ofpoisoning attacks in online learning settings.
AU  - Collinge,G
AU  - Lupu,E
AU  - Munoz,Gonzalez L
PB  - ESANN
PY  - 2019///
TI  - Defending against Poisoning Attacks in Online Learning Settings
UR  - http://hdl.handle.net/10044/1/70348
ER  -
Download