Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models

Duanyi Yao, Changyue Li, Zhicong Huang, Cheng Hong, Songze Li

Abstract

Vision-Language Models (VLMs) are increasingly deployed in consumer applications where users seek recommendations about products, dining, and services. We introduce Hidden Ads, a new class of backdoor attacks that exploit this recommendation-seeking behavior to inject unauthorized advertisements. Unlike traditional pattern-triggered backdoors that rely on artificial triggers such as pixel patches or special tokens, Hidden Ads activates on natural user behaviors: when users upload images containi

Categories

Cite This Resource

@article{llmsec202600157,
  title = {Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models},
  author = {Duanyi Yao and Changyue Li and Zhicong Huang and Cheng Hong and Songze Li},
  year = {2026},
  url = {https://arxiv.org/abs/2603.27522},
}