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 recent years, financial fraud detection systems have become very efficientat detecting fraud, which is a major threat faced by e-commerce platforms. Suchsystems often include machine learning-based algorithms aimed at detecting andreporting fraudulent activity. In this paper, we examine the application ofadversarial learning based ranking techniques in the fraud detection domain andpropose FRAUDability, a method for the estimation of a financial frauddetection system's performance for every user. We are motivated by theassumption that "not all users are created equal" -- while some users are wellprotected by fraud detection algorithms, others tend to pose a challenge tosuch systems. The proposed method produces scores, namely "fraudabilityscores," which are numerical estimations of a fraud detection system's abilityto detect financial fraud for a specific user, given his/her unique activity inthe financial system. Our fraudability scores enable those tasked withdefending users in a financial platform to focus their attention and resourceson users with high fraudability scores to better protect them. We validate ourmethod using a real e-commerce platform's dataset and demonstrate theapplication of fraudability scores from the attacker's perspective, on theplatform, and more specifically, on the fraud detection systems used by thee-commerce enterprise. We show that the scores can also help attackers increasetheir financial profit by 54%, by engaging solely with users with highfraudability scores, avoiding those users whose spending habits enable moreaccurate fraud detection.

FRAUDability: Estimating Users' Susceptibility to Financial Fraud Using Adversarial Machine Learning