Adversarial attacks threaten vision language models in self driving cars

Transferable Spatial Temporal Coherence Adversarial Attack on Black-Box Vision Language Models for Autonomous Driving

Computer Vision and Pattern RecognitionArtificial Intelligence

Summary

Autonomous cars use video-based vision language models (VLMs) to understand their surroundings. This paper shows that these models can be fooled by subtle changes in video frames that confuse the system over time. The authors created a new attack that picks key video frames and changes them in ways that disrupt how the model reads the video sequence, all without knowing the model's inner workings. Their tests show current models remain vulnerable, highlighting the need for better defenses in self-driving technology.

What this means in practice

  • For autonomous vehicle engineers: Evaluate and improve the robustness of vision language models in self-driving systems against temporal adversarial attacks on video data.
  • For security teams for ai systems: Design better defense strategies to protect autonomous driving perception models from black-box adversarial video attacks that disrupt temporal consistency.

Authors

Heyam Bin Jahlan Areej Alhothali Abeer Alhothali

Abstract

The rapid integration of Vision Language Models (VLMs) into sensitive systems introduces critical safety vulnerabilities that remain unexplored in exist studies. While adversarial attack robustness has been extensively studied for image-based models, the susceptibility of VLMs to temporally-aware adversarial attacks against video in driving context poses a distinct and under examined threat. In this paper, we introduce novel adversarial attack against video targeting VLM models used for autonomous driving scenes named Spatial Temporal Coherence Adversarial Attack (STCA). Our attack comprise from three stages: modalities expansion, Spatial attack, and STCA attack. In modalities expansion, we propose caption-guided frame selection method in order to ensure that adversarial perturbation target the most semantically significant frames. Secondly.In spatial attack, we craft effective perturbation and preserve high similarity. Then the perturbed video generated fed into STCA stage that disrupt cross-frame temporal coherence using motion guided mask. Our method operate under black box threat model against victim target VLMs, relying solely on transferability from white-box surrogate model.We conduct our experiments on the BDD100K and nuScenes autonomous driving datasets across three VLM models: Video LLaVA-7B, Qwen2.5-VL-7B, and Dolphin. Experimental results demonstrate spatial attack achieves an ASR with high SSIM. Our finding reveal that existing video language model, remain highly susceptible to adversarial attack in autonomous driving scenarios, underscoring the urgent need for robust defense for VLM models.