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

Many business applications involve adversarial relationships in which bothsides adapt their strategies to optimize their opposing benefits. One of thekey characteristics of these applications is the wide range of strategies thatan adversary may choose as they adapt their strategy dynamically to sustainbenefits and evade authorities. In this paper, we present a novel way ofapproaching these types of applications, in particular in the context ofAnti-Money Laundering. We provide a mechanism through which diverse, realisticand new unobserved behavior may be generated to discover potential unobservedadversarial actions to enable organizations to preemptively mitigate theserisks. In this regard, we make three main contributions. (a) Propose a novelbehavior-based model as opposed to individual transactions-based modelscurrently used by financial institutions. We introduce behavior traces asenriched relational representation to represent observed human behavior. (b) Amodelling approach that observes these traces and is able to accurately inferthe goals of actors by classifying the behavior into money laundering orstandard behavior despite significant unobserved activity. And (c) a syntheticbehavior simulator that can generate new previously unseen traces. Thesimulator incorporates a high level of flexibility in the behavioral parametersso that we can challenge the detection algorithm. Finally, we provideexperimental results that show that the learning module (automatedinvestigator) that has only partial observability can still successfully inferthe type of behavior, and thus the simulated goals, followed by customers basedon traces - a key aspiration for many applications today.

Simulating and classifying behavior in adversarial environments based on action-state traces: an application to money laundering