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

Key points

• The rapid integration of Vision Language Models (VLMs) into sensitive systems introduces critical safety vulnerabilities that remain unexplored in exist studies.1
• 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.1
• In modalities expansion, we propose caption-guided frame selection method in order to ensure that adversarial perturbation target the most semantically significant frames.1
• 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.1

Sources (1)

• [1]Transferable Spatial Temporal Coherence Adversarial Attack on Black-Box Vision Language Models for Autonomous Driving
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 01:30 PM

  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).

  The rapid integration of Vision Language Models (VLMs) into sensitive systems introduces critical safety vulnerabilities that remain unexplored in exist studies.

Extractive summary: sentences quoted from the sources.