Evasion attacks against machine learning at test time

BIGGIO, BATTISTA;CORONA, IGINO;MAIORCA, DAVIDE;GIACINTO, GIORGIO;ROLI, FABIO
2013

Abstract

In security-sensitive applications, the success of machine learning depends on a thorough vetting of their resistance to adversarial data. In one pertinent, well-motivated attack scenario, an adversary may attempt to evade a deployed system at test time by carefully manipulating attack samples. In this work, we present a simple but effective gradient-based approach that can be exploited to systematically assess the security of several, widely-used classification algorithms against evasion attacks. Following a recently proposed framework for security evaluation, we simulate attack scenarios that exhibit different risk levels for the classifier by increasing the attacker's knowledge of the system and her ability to manipulate attack samples. This gives the classifier designer a better picture of the classifier performance under evasion attacks, and allows him to perform a more informed model selection (or parameter setting). We evaluate our approach on the relevant security task of malware detection in PDF files, and show that such systems can be easily evaded. We also sketch some countermeasures suggested by our analysis.
Inglese
Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases - ECML PKDD 2013 - Part III
978-3-642-40993-6
Springer
BERLIN HEIDELBERG
Blockeel H, Kersting K, Nijssen S, Zelezny F
8190
387
402
16
http://link.springer.com/chapter/10.1007/978-3-642-40994-3_25
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2013
Esperti anonimi
2013
Prague, Czech Republic
internazionale
scientifica
4 Contributo in Atti di Convegno (Proceeding)::4.1 Contributo in Atti di convegno
Biggio, Battista; Corona, Igino; Maiorca, Davide; Nelson, B; Srndic, N; Laskov, P; Giacinto, Giorgio; Roli, Fabio
273
8
4.1 Contributo in Atti di convegno
reserved
info:eu-repo/semantics/conferencePaper
Files in This Item:
File Size Format  
Evasion attacks against machine learning at test time.pdf

Solo gestori archivio

Size 475.26 kB
Format Adobe PDF
475.26 kB Adobe PDF & nbsp; View / Open   Request a copy
biggio13-ecml.pdf

Solo gestori archivio

Size 401.93 kB
Format Adobe PDF
401.93 kB Adobe PDF & nbsp; View / Open   Request a copy
Biggio13-ecml.pdf

Solo gestori archivio

Size 473.78 kB
Format Adobe PDF
473.78 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