Research
Covert Visual Prompt Injection against Commercial Multimodal Large Language Models
Publication date not yet evaluated · Added arxiv.org
Page published
Coverage timeline
Single-source research — one report is available.
Why it matters
Covert visual prompt injection lets attackers hide malicious instructions inside seemingly benign images that fool deployed multimodal AI systems without any human-visible cues, expanding the prompt-injection attack surface for defenders.
A research paper by Meiwen Ding and colleagues presents a covert visual prompt injection attack against commercial closed-source multimodal large language models (MLLMs). The method embeds imperceptible adversarial perturbations and a bounded text overlay into an input image, iteratively optimizing feature alignment with malicious visual and textual targets to smuggle instructions past human observers and transfer across multiple MLLMs.