Vision-Language Models (VLMs) are rapidly replacing unimodal encoders in modern retrieval and recommendation systems. While their capabilities are well-documented, their robustness against adversarial manipulation in competitive ranking scenarios remains largely unexplored. In this paper, we uncover a critical vulnerability in VLM-based product search: multimodal ranking attacks. We present Multimodal Generative Engine Optimization (MGEO), a novel adversarial framework that enables a malicious actor to unfairly promote a target product by jointly optimizing imperceptible image perturbations and fluent textual suffixes. Unlike existing attacks that treat modalities in isolation, MGEO employs an alternating gradient-based optimization strategy to exploit the deep cross-modal coupling within the VLM. Extensive experiments on real-world datasets using state-of-the-art models demonstrate that our coordinated attack significantly outperforms text-only and image-only baselines. These findings reveal that multimodal synergy, typically a strength of VLMs, can be weaponized to compromise the integrity of search rankings without triggering conventional content filters.
@article{arxiv.2601.12263,
title = {Multimodal Generative Engine Optimization: Rank Manipulation for Vision-Language Model Rankers},
author = {Yixuan Du and Chenxiao Yu and Haoyan Xu and Ziyi Wang and Yue Zhao and Xiyang Hu},
journal= {arXiv preprint arXiv:2601.12263},
year = {2026}
}