AI RESEARCH

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

arXiv CS.LG

ArXi:2603.27522v1 Announce Type: cross Vision-Language Models (VLMs) are increasingly deployed in consumer applications where users seek recommendations about products, dining, and services. We We propose a multi-tier threat framework to systematically evaluate Hidden Ads across three adversary capability levels: hard prompt injection, soft prompt optimization, and supervised fine-tuning. Our poisoned data generation pipeline uses teacher VLM-generated chain-of-thought reasoning to create natural trigger--slogan associations across multiple semantic domains.