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

In this paper, we describe a new algorithm called Preferential Attachmentk-class Classifier (PreAttacK) for detecting fake accounts in a social network.Recently, several algorithms have obtained high accuracy on this problem.However, they have done so by relying on information about fake accounts'friendships or the content they share with others--the very things we seek toprevent. PreAttacK represents a significant departure from these approaches. Weprovide some of the first detailed distributional analyses of how new fake (andreal) accounts first attempt to request friends after joining a major network(Facebook). We show that even before a new account has made friends or sharedcontent, these initial friend request behaviors evoke a natural multi-classextension of the canonical Preferential Attachment model of social networkgrowth. We use this model to derive a new algorithm, PreAttacK. We prove thatin relevant problem instances, PreAttacK near-optimally approximates theposterior probability that a new account is fake under this multi-classPreferential Attachment model of new accounts' (not-yet-answered) friendrequests. These are the first provable guarantees for fake account detectionthat apply to new users, and that do not require strong homophily assumptions.This principled approach also makes PreAttacK the only algorithm with provableguarantees that obtains state-of-the-art performance on new users on the globalFacebook network, where it converges to AUC=0.9 after new users send + receivea total of just 20 not-yet-answered friend requests. For comparison,state-of-the-art benchmarks do not obtain this AUC even after observingadditional data on new users' first 100 friend requests. Thus, unlikemainstream algorithms, PreAttacK converges before the median new fake accounthas made a single friendship (accepted friend request) with a human.

Preemptive Detection of Fake Accounts on Social Networks via Multi-Class Preferential Attachment Classifiers