Paper Info
Title
Is data clustering in adversarial settings secure?
Abstract
Clustering algorithms have been increasingly adopted in security applications to spot dangerous or illicit activities. However, they have not been originally devised to deal with deliberate attack attempts that may aim to subvert the clustering process itself. Whether clustering can be safely adopted in such settings remains thus questionable. In this work we propose a general framework that allows one to identify potential attacks against clustering algorithms, and to evaluate their impact, by making specific assumptions on the adversary's goal, knowledge of the attacked system, and capabilities of manipulating the input data. We show that an attacker may significantly poison the whole clustering process by adding a relatively small percentage of attack samples to the input data, and that some attack samples may be obfuscated to be hidden within some existing clusters. We present a case study on single-linkage hierarchical clustering, and report experiments on clustering of malware samples and handwritten digits.
Year
DOI
Venue
2013
10.1145/2517312.2517321
AISec
Keywords
Field
DocType
existing cluster,deliberate attack attempt,adversarial setting,clustering process,clustering algorithm,input data,case study,attack sample,single-linkage hierarchical clustering,whole clustering process,potential attack,clustering,computer security,unsupervised learning
Hierarchical clustering,Data mining,Computer science,Unsupervised learning,Adversary,Malware,Obfuscation,Cluster analysis,Adversarial system
Conference
Volume
ISSN
Citations 
abs/1811.09982
Proceedings of the 2013 ACM Workshop on Artificial Intelligence and Security, AISec '13, pages 87-98, New York, NY, USA, 2013. ACM
15
PageRank 
References 
Authors
0.65
20
6
Name
Order
Citations
PageRank
Battista Biggio1122473.49
Ignazio Pillai220312.17
Samuel Rota Bulò356433.69
Davide Ariu428716.40
Marcello Pelillo51888150.33
Fabio Roli64846311.69