mlsanityData to 14 Oct 2026

Technical Report on the CVPR 2026@AdvML Workshop Challenge

arXiv 2607.11560 ↗First posted 13 Jul 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Vision-language agents (VLAs) are increasingly used to interpret complex driving scenes and support safety-critical reasoning. This report presents the CVPR 2026@AdvML Workshop Challenge on adversarial multimodal attacks against autonomous-driving VLAs. Built on DriveLM-style multi-view visual question answering, the challenge represents each scene with six synchronized camera images and a structured collection of driving-related question-answer pairs. Participants generate adversarial images and suffix-only textual perturbations that induce model responses to deviate from reference answers while preserving image fidelity and limiting textual cost. The competition comprises two phases, with Phase II adding a hidden black-box model to assess transferability. We describe the task design, submission rules, evaluation protocol, and leaderboard results, and then examine five leading submissions for which technical reports were available. Across these reports, several recurring patterns emerge: image-side attacks are favored by the suffix penalty; scene-level, multi-view optimization is more effective than treating views in isolation; QA types and graph structure provide useful priors for allocating attack budget; feature-space objectives can improve black-box transfer; and typographic content embedded in camera images exposes a persistent vulnerability in driving VLAs. These findings provide a practical reference for future robustness evaluation and defense design in multimodal autonomous-driving systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 31 references that are in the map. First posted on arXiv 13 Jul 2026.

Builds on

26 of 31 references.

References · 26

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Visual Instruction Tuningcited by 7,869
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  6. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  7. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  8. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  9. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  10. 2023LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Modelcited by 602
  11. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  12. 2023DriveLM: Driving with Graph Visual Question Answeringcited by 536
14 more
  1. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 442
  2. 2023FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Promptscited by 398
  3. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 355
  4. 2023Visual Adversarial Examples Jailbreak Aligned Large Language Modelscited by 328
  5. 2023On Evaluating Adversarial Robustness of Large Vision-Language Modelscited by 284
  6. 2023Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Modelscited by 273
  7. 2023Dolphins: Multimodal Language Model for Drivingcited by 124
  8. 2023VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Modelscited by 68
  9. 2025A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluationscited by 67
  10. 2023Boosting Adversarial Transferability by Block Shuffle and Rotationcited by 64
  11. 2024Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attackscited by 39
  12. 2024Visual Adversarial Attack on Vision-Language Models for Autonomous Drivingcited by 36
  13. 2022RSTAM: An Effective Black-Box Impersonation Attack on Face Recognition using a Mobile and Compact Printercited by 7
  14. 2026Multi-Paradigm Collaborative Adversarial Attack Against Multi-Modal Large Language Modelscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving
  2. 2025Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models
  3. 2026Understanding Adversarial Transferability in Vision-Language Models for Autonomous Driving: A Cross-Architecture Analysis
  4. 2026Where Does the Answer Come From? Benchmarking View-Level Visual Evidence Identification in Multi-View MLLMs for Autonomous Driving
  5. 2025Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives
  6. 2025TinyDrive: Multiscale Visual Question Answering with Selective Token Routing for Autonomous Driving
  7. 2025DynRsl-VLM: Enhancing Autonomous Driving Perception with Dynamic Resolution Vision-Language Models
  8. 2025CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model