Paper Info
Title
One-and-a-Half-Class Multiple Classifier Systems for Secure Learning Against Evasion Attacks at Test Time
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-half-class (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.
Year
DOI
Venue
2015
10.1007/978-3-319-20248-8_15
Lecture Notes in Computer Science
Field
DocType
Volume
Feature vector,Computer science,Decision function,Artificial intelligence,Data manipulation language,Malware,Classifier (linguistics),Machine learning,Adversarial system
Conference
9132
ISSN
Citations 
PageRank 
0302-9743
11
0.51
References 
Authors
17
7
Name
Order
Citations
PageRank
Battista Biggio1122473.49
Igino Corona258626.01
Zhimin He353635.90
Patrick P. K. Chan427133.82
Giorgio Giacinto52196125.33
Daniel S. Yeung6112692.97
Fabio Roli74846311.69