One-and-a-half-class multiple classifier systems for secure learning against evasion attacks at test time

BIGGIO, BATTISTA;CORONA, IGINO;GIACINTO, GIORGIO;ROLI, FABIO
2015

Abstract

Pattern classifiers have been widely used in adversarial settings like spam and malware detection, although they have not been originally designed to cope with intelligent attackers that manipulate data at test time to evade detection. While a number of adversary-aware learning algorithms have been proposed, they are computationally demanding and aim to counter specific kinds of adversarial data manipulation. In this work, we overcome these limitations by proposing a multiple classifier system capable of improving security against evasion attacks at test time by learning a decision function that more tightly encloses the legitimate samples in feature space, without significantly compromising accuracy in the absence of attack. Since we combine a set of one-class and two-class classifiers to this end, we name our approach one-and-a-halfclass (1.5C) classification. Our proposal is general and it can be used to improve the security of any classifier against evasion attacks at test time, as shown by the reported experiments on spam and malware detection
Inglese
Multiple Classifier Systems
978-3-319-20247-1
978-3-319-20248-8
978-3-319-20247-1
978-3-319-20248-8
Springer Verlag
HEIDELBERGER PLATZ 3, D-14197 BERLIN, GERMANY
GERMANIA
Friedhelm Schwenker, Fabio Roli, Josef Kittler
9132
168
180
13
12th International Workshop, MCS 2015
Esperti anonimi
June 29 - July 1, 2015
Günzburg, Germany,
internazionale
scientifica
4 Contributo in Atti di Convegno (Proceeding)::4.1 Contributo in Atti di convegno
Biggio, Battista; Corona, Igino; He, Z. M.; Chan P., P; Giacinto, Giorgio; Yeung D., S; Roli, Fabio
273
7
4.1 Contributo in Atti di convegno
reserved
info:eu-repo/semantics/conferencePaper
Files in This Item:
File Size Format  
chp%3A10.1007%2F978-3-319-20248-8_15.pdf

Solo gestori archivio

Type: versione editoriale
Size 463.78 kB
Format Adobe PDF
463.78 kB Adobe PDF & nbsp; View / Open   Request a copy

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Questionnaire and social

Share on:
Impostazioni cookie