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: Geigel, Arturo; *
Affiliations: Electrical Engineering Department, Polytechnic University of Puerto Rico, Hato Rey, Puerto Rico. E-mail: ageigel@pupr.edu
Correspondence: [*] Address for correspondence: Arturo Geigel, Electrical Engineering Department, Polytechnic University of Puerto Rico, 377 Ponce de Leon Ave, Hato Rey, 00918 Puerto Rico. Tel.: +1 787 622 8000, ext. 340, 472; E-mail: ageigel@pupr.edu
Abstract: This paper presents a proof of concept of a neural network Trojan. The neural network Trojan consists of a neural network that has been trained with a compromised dataset and modified code. The Trojan implementation is carried out by insertion of a malicious payload encoded into the weights alongside with the data of the intended application. The neural Trojan is specifically designed so that when a specific entry is fed into the trained neural network, it triggers the interpretation of the data as payload. The paper presents a background on which this attack is based and provides the assumptions that make the attack possible. Two embodiments of the attack are presented consisting of a basic backpropagation network and a Neural Network Trojan with Sequence Processing Connections (NNTSPC). The two alternatives are used depending on the underlying circumstances on which the compromise is launched. Experimental results are carried out with synthetic as well as a chosen existing binary payload. Practical issues of the attack are also discussed, as well as a discussion on detection techniques.
Keywords: Neural network, Trojan, malware, artificial intelligence, machine learning
DOI: 10.3233/JCS-2012-0460
Journal: Journal of Computer Security, vol. 21, no. 2, pp. 191-232, 2013
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
USA
Tel: +1 703 830 6300
Fax: +1 703 830 2300
sales@iospress.com
For editorial issues, like the status of your submitted paper or proposals, write to editorial@iospress.nl
IOS Press
Nieuwe Hemweg 6B
1013 BG Amsterdam
The Netherlands
Tel: +31 20 688 3355
Fax: +31 20 687 0091
info@iospress.nl
For editorial issues, permissions, book requests, submissions and proceedings, contact the Amsterdam office info@iospress.nl
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
china@iospress.cn
For editorial issues, like the status of your submitted paper or proposals, write to editorial@iospress.nl
如果您在出版方面需要帮助或有任何建, 件至: editorial@iospress.nl