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{Paudice:2019:10.1007/978-3-030-13453-2_1,
author = {Paudice, A and Muñoz-González, L and Lupu, EC},
doi = {10.1007/978-3-030-13453-2_1},
pages = {5--15},
publisher = {Springer Verlag},
title = {Label sanitization against label flipping poisoning attacks},
url = {http://dx.doi.org/10.1007/978-3-030-13453-2_1},
year = {2019}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Many machine learning systems rely on data collected in thewild from untrusted sources, exposing the learning algorithms to datapoisoning. Attackers can inject malicious data in the training datasetto subvert the learning process, compromising the performance of thealgorithm producing errors in a targeted or an indiscriminate way. Labelflipping attacks are a special case of data poisoning, where the attackercan control the labels assigned to a fraction of the training points. Evenif the capabilities of the attacker are constrained, these attacks havebeen shown to be effective to significantly degrade the performance ofthe system. In this paper we propose an efficient algorithm to performoptimal label flipping poisoning attacks and a mechanism to detect andrelabel suspicious data points, mitigating the effect of such poisoningattacks.
AU  - Paudice,A
AU  - Muñoz-González,L
AU  - Lupu,EC
DO  - 10.1007/978-3-030-13453-2_1
EP  - 15
PB  - Springer Verlag
PY  - 2019///
SN  - 0302-9743
SP  - 5
TI  - Label sanitization against label flipping poisoning attacks
UR  - http://dx.doi.org/10.1007/978-3-030-13453-2_1
UR  - https://link.springer.com/chapter/10.1007%2F978-3-030-13453-2_1
UR  - http://hdl.handle.net/10044/1/64581
ER  -
Download