Research · curated 19 Jul 2026
Devil in the Lens: Analyzing and Defending Physical Prompt Injection Against Vision-Language Models on Wearable Devices
First reported arxiv.org
Coverage timeline
Single-source research — first reported, latest, and curated coincide.
Why it matters
Physical prompt injection shows that VLM-powered wearables can be manipulated by ordinary environmental text to produce unsafe or false guidance, posing real-world safety risks to users who trust these embodied AI assistants.
A research paper, "Devil in the Lens," characterizes physical prompt injection attacks against Vision-Language Models on wearable devices such as AI glasses, where malicious text embedded in real-world environments acts as an indirect prompt-injection channel that hijacks model behavior. Using photos captured from AI glasses across 200+ environments, the authors identify 6 threat vectors, evaluate 12 VLMs (achieving attack success rates up to 96% simulated and 60% real-world), and propose two defenses: a mask-based external filter and a semantic-vector-based internal detector.