Non-Intrusive Graph-Based Bot Detection for E-Commerce Using Inductive Graph Neural Networks

TL;DR

This paper introduces a non-intrusive, graph-based bot detection method for e-commerce that uses inductive graph neural networks to accurately identify malicious bots by modeling user session behavior.

Contribution

It presents a novel, deployment-friendly framework leveraging inductive graph neural networks for effective, real-time bot detection without intrusive client-side measures.

Findings

Outperforms baseline models in AUC and F1 score

Remains robust under graph perturbations

Generalizes well to unseen sessions and URLs

Abstract

Malicious bots pose a growing threat to e-commerce platforms by scraping data, hoarding inventory, and perpetrating fraud. Traditional bot mitigation techniques, including IP blacklists and CAPTCHA-based challenges, are increasingly ineffective or intrusive, as modern bots leverage proxies, botnets, and AI-assisted evasion strategies. This work proposes a non-intrusive graph-based bot detection framework for e-commerce that models user session behavior through a graph representation and applies an inductive graph neural network for classification. The approach captures both relational structure and behavioral semantics, enabling accurate identification of subtle automated activity that evades feature-based methods. Experiments on real-world e-commerce traffic demonstrate that the proposed inductive graph model outperforms a strong session-level multilayer perceptron baseline in terms of AUC and F1 score. Additional adversarial perturbation and cold-start simulations show that the model remains robust under moderate graph modifications and generalizes effectively to previously unseen sessions and URLs. The proposed framework is deployment-friendly, integrates with existing systems without client-side instrumentation, and supports real-time inference and incremental updates, making it suitable for practical e-commerce security deployments.