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

Guaranteeing the security of transactional systems is a crucial priority ofall institutions that process transactions, in order to protect theirbusinesses against cyberattacks and fraudulent attempts. Adversarial attacksare novel techniques that, other than being proven to be effective to foolimage classification models, can also be applied to tabular data. Adversarialattacks aim at producing adversarial examples, in other words, slightlymodified inputs that induce the Artificial Intelligence (AI) system to returnincorrect outputs that are advantageous for the attacker. In this paper weillustrate a novel approach to modify and adapt state-of-the-art algorithms toimbalanced tabular data, in the context of fraud detection. Experimentalresults show that the proposed modifications lead to a perfect attack successrate, obtaining adversarial examples that are also less perceptible whenanalyzed by humans. Moreover, when applied to a real-world production system,the proposed techniques shows the possibility of posing a serious threat to therobustness of advanced AI-based fraud detection procedures.

Adversarial Attacks for Tabular Data: Application to Fraud Detection and Imbalanced Data