Prompt Injection Via Road Signs
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.