CHAI: Command Hijacking against embodied AI
This work addresses a critical security problem for developers and users of embodied AI systems, highlighting vulnerabilities in multimodal reasoning that could lead to real-world safety issues.
The paper tackles the security risks of embodied AI systems by introducing CHAI, a prompt-based attack that embeds deceptive instructions in visual inputs to hijack commands, and demonstrates that it consistently outperforms state-of-the-art attacks on tasks like drone emergency landing and autonomous driving.
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, and aerial object tracking, and on 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.