Prompt Injection Via Road Signs

Published: (February 11, 2026 at 07:03 AM EST)
1 min read

Source: Schneier on Security

Abstract

Embodied Artificial Intelligence (AI) promises to handle edge cases in robotic vehicle systems where data is scarce by using common‑sense reasoning grounded in perception and action to generalize beyond training distributions and adapt to novel real‑world situations. These capabilities, however, also create new security risks. In this paper, we introduce CHAI (Command Hijacking against embodied AI), a new class of prompt‑based attacks that exploit the multimodal language interpretation abilities of Large Visual‑Language Models (LVLMs). CHAI embeds deceptive natural language instructions, such as misleading signs, in visual input, systematically searches the token space, builds a dictionary of prompts, and guides an attacker model to generate Visual Attack Prompts. We evaluate CHAI on four LVLM agents—drone emergency landing, autonomous driving, aerial object tracking, and a real robotic vehicle. Our experiments show that CHAI consistently outperforms state‑of‑the‑art attacks. By exploiting the semantic and multimodal reasoning strengths of next‑generation embodied AI systems, CHAI underscores the urgent need for defenses that extend beyond traditional adversarial robustness.

News article

0 views
Back to Blog

Related posts

Read more »

Friday Squid Blogging: Do Squid Dream?

Friday Squid Blogging: Do Squid Dream? An explorationhttps://sharksandco.com/do-squid-dream-what-scientists-think-about-cephalopod-sleep-1-4236/ of the interes...

Rewiring Democracy Ebook is on Sale

I just noticed that the ebook version of Rewriring Democracy is on sale for $5 on Amazonhttps://www.amazon.com/gp/product/B0DTNZ2H86, Apple Bookshttps://books.a...