Pith. sign in

REVIEW 8 cited by

Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2501.13563 v1 pith:KHNQY7PC submitted 2025-01-23 cs.CV cs.AI

Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving

classification cs.CV cs.AI
keywords adversarialattacksdrivingblack-boxvlmsmodelsreasoningremain
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities; however, these models remain highly susceptible to adversarial attacks. While existing research has explored white-box attacks to some extent, the more practical and challenging black-box scenarios remain largely underexplored due to their inherent difficulty. In this paper, we take the first step toward designing black-box adversarial attacks specifically targeting VLMs in AD. We identify two key challenges for achieving effective black-box attacks in this context: the effectiveness across driving reasoning chains in AD systems and the dynamic nature of driving scenarios. To address this, we propose Cascading Adversarial Disruption (CAD). It first introduces Decision Chain Disruption, which targets low-level reasoning breakdown by generating and injecting deceptive semantics, ensuring the perturbations remain effective across the entire decision-making chain. Building on this, we present Risky Scene Induction, which addresses dynamic adaptation by leveraging a surrogate VLM to understand and construct high-level risky scenarios that are likely to result in critical errors in the current driving contexts. Extensive experiments conducted on multiple AD VLMs and benchmarks demonstrate that CAD achieves state-of-the-art attack effectiveness, significantly outperforming existing methods (+13.43% on average). Moreover, we validate its practical applicability through real-world attacks on AD vehicles powered by VLMs, where the route completion rate drops by 61.11% and the vehicle crashes directly into the obstacle vehicle with adversarial patches. Finally, we release CADA dataset, comprising 18,808 adversarial visual-question-answer pairs, to facilitate further evaluation and research in this critical domain. Our codes and dataset will be available after paper's acceptance.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agents

    cs.LG 2026-05 unverdicted novelty 7.0

    WMAttack automates finite-budget attack search for world-model agents via SCAS and RGAR, reporting higher normalized reward drops than baselines on Atari and DMC tasks.

  2. ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving

    cs.CR 2026-05 unverdicted novelty 6.0

    ReasonBreak demonstrates up to 89% attack success on reasoning and 72% on trajectories in NVIDIA Alpamayo VLA models via black-box textual perturbations, introducing a reasoning-aware evaluation framework and benchmar...

  3. GuardAD: Safeguarding Autonomous Driving MLLMs via Markovian Safety Logic

    cs.AI 2026-05 unverdicted novelty 6.0

    GuardAD reduces accident rates by 32% in autonomous driving MLLMs by using n-th order Markovian logic to infer latent hazards and revise actions.

  4. High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models

    cs.CV 2025-12 unverdicted novelty 6.0

    High-entropy tokens act as concentrated multimodal failure points in VLMs, enabling sparse Entropy-Guided Attacks that achieve 93-95% success and 30-38% harmful rates with cross-model transfer.

  5. Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective

    cs.CV 2026-07 conditional novelty 5.0

    Environmental illusions cause 5-7% accuracy drops in lane detection models and can trigger collisions in closed-loop simulation, with a proposed defense (MIDA) recovering ~4% robustness.

  6. Adversarial Flow Matching for Imperceptible Attacks on End-to-End Autonomous Driving

    cs.CV 2026-04 unverdicted novelty 5.0

    AFM is a novel gray-box adversarial attack using flow matching to create visually imperceptible perturbations that degrade performance of Vision-Language-Action and modular end-to-end autonomous driving models while s...

  7. A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models

    cs.CV 2026-04 unverdicted novelty 5.0

    A patch-augmented cross-view regularization method reduces backdoor attack success rates in multimodal LLMs by enforcing output differences between original and perturbed views while using entropy constraints to prese...

  8. Missing-by-Design: Certifiable Modality Deletion for Revocable Multimodal Sentiment Analysis

    cs.CL 2026-02 unverdicted novelty 5.0

    Missing-by-Design learns property-aware embeddings and uses saliency-driven Gaussian updates to produce machine-verifiable certificates that remove a chosen modality without full retraining.