← Search

Zulfikar Alom

2 accepted papers

2026

BOCLOAK: Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection

ICML 2026poster

The rise of bot accounts on social media poses significant risks to public discourse. To address this threat, modern bot detectors increasingly rely on Graph Neural Networks (GNNs). However, the effectiveness of these GNN-based detectors in real-world settings remains poorly understood. In practice,…

Cited by 0SourceScholar
2025

GOttack: Universal Adversarial Attacks on Graph Neural Networks via Graph Orbits Learning

ICLR 2025poster

Graph Neural Networks (GNNs) have demonstrated superior performance in node classification tasks across diverse applications. However, their vulnerability to adversarial attacks, where minor perturbations can mislead model predictions, poses significant challenges. This study introduces GOttack, a n…