Searching for just a few words should be enough to get started. If you need to make more complex queries, use the tips below to guide you.
Article type: Research Article
Authors: Calzavara, Stefano; * | Ferrara, Pietro | Lucchese, Claudio
Affiliations: Università Ca’ Foscari Venezia, Italy
Correspondence: [*] Corresponding author. E-mail: [email protected].
Abstract: Machine learning has proved invaluable for a range of different tasks, yet it also proved vulnerable to evasion attacks, i.e., maliciously crafted perturbations of inputs designed to force mispredictions. In this article we propose a novel technique to certify the security of machine learning models against evasion attacks with respect to an expressive threat model, where the attacker can be represented by an arbitrary imperative program. Our approach is based on a transformation of the model under attack into an equivalent imperative program, which is then analyzed using the traditional abstract interpretation framework. This solution is sound, efficient and general enough to be applied to a range of different models, including decision trees, logistic regression and neural networks. Our experiments on publicly available datasets show that our technique yields only a minimal number of false positives and scales up to cases which are intractable for a competitor approach.
Keywords: Adversarial machine learning, abstract interpretation, evasion attacks, security certification
DOI: 10.3233/JCS-210133
Journal: Journal of Computer Security, vol. 31, no. 1, pp. 57-84, 2023
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
USA
Tel: +1 703 830 6300
Fax: +1 703 830 2300
[email protected]
For editorial issues, like the status of your submitted paper or proposals, write to [email protected]
IOS Press
Nieuwe Hemweg 6B
1013 BG Amsterdam
The Netherlands
Tel: +31 20 688 3355
Fax: +31 20 687 0091
[email protected]
For editorial issues, permissions, book requests, submissions and proceedings, contact the Amsterdam office [email protected]
Inspirees International (China Office)
Ciyunsi Beili 207(CapitaLand), Bld 1, 7-901
100025, Beijing
China
Free service line: 400 661 8717
Fax: +86 10 8446 7947
[email protected]
For editorial issues, like the status of your submitted paper or proposals, write to [email protected]
如果您在出版方面需要帮助或有任何建, 件至: [email protected]