Security Evaluation of Support Vector Machines in Adversarial Environments

BIGGIO, BATTISTA;CORONA, IGINO;NELSON, BLAINE ALAN;MAIORCA, DAVIDE;FUMERA, GIORGIO;GIACINTO, GIORGIO;ROLI, FABIO
2014

Abstract

Support vector machines (SVMs) are among the most popular classification techniques adopted in security applications like malware detection, intrusion detection, and spam filtering. However, if SVMs are to be incorporated in real-world security systems, they must be able to cope with attack patterns that can either mislead the learning algorithm (poisoning), evade detection (evasion) or gain information about their internal parameters (privacy breaches). The main contributions of this chapter are twofold. First, we introduce a formal general framework for the empirical evaluation of the security of machine-learning systems. Second, according to our framework, we demonstrate the feasibility of evasion, poisoning and privacy attacks against SVMs in real-world security problems. For each attack technique, we evaluate its impact and discuss whether (and how) it can be countered through an adversary-aware design of SVMs. Our experiments are easily reproducible thanks to open-source code that we have made available, together with all the employed datasets, on a public repository.
eng
Support Vector Machines Applications
Ashwini Shukla; Aude Billard; et al
Ma Y; Guo G
105
153
49
Springer International Publishing
-
CHE
978-3-319-02299-4
http://link.springer.com/chapter/10.1007%2F978-3-319-02300-7_4
Esperti anonimi
internazionale
Scientifica
si
info:eu-repo/semantics/bookPart
2.1 Contributo in volume (Capitolo o Saggio)
Biggio B; Corona I; Nelson BA; Rubinstein BIP; Maiorca D; Fumera G; Giacinto G; Roli F
2 Contributo in Volume::2.1 Contributo in volume (Capitolo o Saggio)
8
268
reserved
File in questo prodotto:
File Dimensione Formato  
biggio14-svm-chapter-submitted.pdf

non disponibili

Dimensione 687.1 kB
Formato Adobe PDF
687.1 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Questionario e social

Condividi su:
Impostazioni cookie