PhysPatch: A Physically Realizable and Transferable Adversarial Patch Attack for Multimodal Large Language Models-based Autonomous Driving Systems
By: Qi Guo , Xiaojun Jia , Shanmin Pang and more
Potential Business Impact:
Tricks self-driving cars with fake stickers.
Multimodal Large Language Models (MLLMs) are becoming integral to autonomous driving (AD) systems due to their strong vision-language reasoning capabilities. However, MLLMs are vulnerable to adversarial attacks, particularly adversarial patch attacks, which can pose serious threats in real-world scenarios. Existing patch-based attack methods are primarily designed for object detection models and perform poorly when transferred to MLLM-based systems due to the latter's complex architectures and reasoning abilities. To address these limitations, we propose PhysPatch, a physically realizable and transferable adversarial patch framework tailored for MLLM-based AD systems. PhysPatch jointly optimizes patch location, shape, and content to enhance attack effectiveness and real-world applicability. It introduces a semantic-based mask initialization strategy for realistic placement, an SVD-based local alignment loss with patch-guided crop-resize to improve transferability, and a potential field-based mask refinement method. Extensive experiments across open-source, commercial, and reasoning-capable MLLMs demonstrate that PhysPatch significantly outperforms prior methods in steering MLLM-based AD systems toward target-aligned perception and planning outputs. Moreover, PhysPatch consistently places adversarial patches in physically feasible regions of AD scenes, ensuring strong real-world applicability and deployability.
Similar Papers
Robust Physical Adversarial Patches Using Dynamically Optimized Clusters
CV and Pattern Recognition
Makes fake pictures fool computers even when resized.
One Patch to Rule Them All: Transforming Static Patches into Dynamic Attacks in the Physical World
Cryptography and Security
Changes car's view with light to trick it.
Towards Powerful and Practical Patch Attacks for 2D Object Detection in Autonomous Driving
CV and Pattern Recognition
Makes self-driving cars safer from fake road signs.