English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Adversarial attacks have been alerting the artificial intelligence communityrecently, since many machine learning algorithms were found vulnerable tomalicious attacks. This paper studies adversarial attacks to scale-freenetworks to test their robustness in terms of statistical measures. In additionto the well-known random link rewiring (RLR) attack, two heuristic attacks areformulated and simulated: degree-addition-based link rewiring (DALR) anddegree-interval-based link rewiring (DILR). These three strategies are appliedto attack a number of strong scale-free networks of various sizes generatedfrom the Barab\'asi-Albert model. It is found that both DALR and DILR are moreeffective than RLR, in the sense that rewiring a smaller number of links cansucceed in the same attack. However, DILR is as concealed as RLR in the sensethat they both are constructed by introducing a relatively small number ofchanges on several typical structural properties such as average shortestpath-length, average clustering coefficient, and average diagonal distance. Theresults of this paper suggest that to classify a network to be scale-free hasto be very careful from the viewpoint of adversarial attack effects.

Adversarial Attacks to Scale-Free Networks: Testing the Robustness of Physical Criteria