Adversarial attacks have been alerting the artificial intelligence community recently since many machine learning algorithms were found vulnerable to malicious attacks. This paper studies adversarial attacks on Broido and Clauset classification for scale-free networks to test its robustness in terms of statistical measures. In addition to the well-known random link rewiring (RLR) attack, two heuristic attacks are formulated and simulated: degree-addition-based link rewiring (DALR) and degree-interval-based link rewiring (DILR). These three strategies are applied to attack a number of strong scale-free networks of various sizes generated from the Barabási–Albert model and the uncorrelated configuration model. It is found that both DALR and DILR are more effective than RLR in the sense that rewiring a smaller number of links can succeed in the same attack. However, DILR is as concealed as RLR in the sense that they both are introducing a relatively small change on several typical structural properties, such as the average shortest path-length, the average clustering coefficient, the average diagonal distance, and the Kolmogorov–Smirnov test of the degree distribution. The results of this paper suggest that to classify a network to be scale-free, one has to be very careful from the viewpoint of adversarial attack effects.
Skip Nav Destination
Article navigation
August 2020
Research Article|
August 03 2020
Adversarial attack on BC classification for scale-free networks
Qi Xuan
;
Qi Xuan
a)
1
Institute of Cyberspace Security, Zhejiang University of Technology
, Hangzhou 310023, China
2
College of Information Engineering, Zhejiang University of Technology
, Hangzhou 310023, China
Search for other works by this author on:
Yalu Shan;
Yalu Shan
b)
1
Institute of Cyberspace Security, Zhejiang University of Technology
, Hangzhou 310023, China
2
College of Information Engineering, Zhejiang University of Technology
, Hangzhou 310023, China
Search for other works by this author on:
Jinhuan Wang;
Jinhuan Wang
c)
1
Institute of Cyberspace Security, Zhejiang University of Technology
, Hangzhou 310023, China
2
College of Information Engineering, Zhejiang University of Technology
, Hangzhou 310023, China
Search for other works by this author on:
Zhongyuan Ruan
;
Zhongyuan Ruan
d)
1
Institute of Cyberspace Security, Zhejiang University of Technology
, Hangzhou 310023, China
2
College of Information Engineering, Zhejiang University of Technology
, Hangzhou 310023, China
d)Author to whom correspondence should be addressed: zyruan@zjut.edu.cn
Search for other works by this author on:
Guanrong Chen
Guanrong Chen
e)
3
Department of Electrical Engineering, City University of Hong Kong
, Hong Kong, China
Search for other works by this author on:
a)
Electronic mail: xuanqi@zjut.edu.cn
b)
Electronic mail: 1223071127@qq.com
c)
Electronic mail: jinhuanwang@zjut.edu.cn
d)Author to whom correspondence should be addressed: zyruan@zjut.edu.cn
e)
Electronic mail: eegchen@cityu.edu.hk
Chaos 30, 083102 (2020)
Article history
Received:
February 05 2020
Accepted:
July 13 2020
Citation
Qi Xuan, Yalu Shan, Jinhuan Wang, Zhongyuan Ruan, Guanrong Chen; Adversarial attack on BC classification for scale-free networks. Chaos 1 August 2020; 30 (8): 083102. https://doi.org/10.1063/5.0003707
Download citation file:
Sign in
Don't already have an account? Register
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Pay-Per-View Access
$40.00
Citing articles via
Sex, ducks, and rock “n” roll: Mathematical model of sexual response
K. B. Blyuss, Y. N. Kyrychko
Focus on the disruption of networks and system dynamics
Peng Ji, Jan Nagler, et al.
Nonlinear comparative analysis of Greenland and Antarctica ice cores data
Berenice Rojo-Garibaldi, Alberto Isaac Aguilar-Hernández, et al.