mlsanityData to 14 Oct 2026

AirflowAttack: Thermal-Airflow Adversarial Perturbations against Infrared Remote-Sensing Vision-Language Models

arXiv 2607.06485 ↗First posted 7 Jul 2026cs.CV cs.AIcited by 0

On the map: Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness

Abstract (arXiv)

Vision-language models (VLMs) are increasingly deployed on infrared (IR) remote sensing imagery in security-critical settings, yet their adversarial robustness remains unexamined. We present AirflowAttack, to our knowledge the first adversarial attack for IR remote-sensing VLMs and the first to weaponize thermal-airflow turbulence as the perturbation prior. A lightweight generator synthesizes a single input-agnostic perturbation regularized toward physically plausible airflow patterns. Optimized on one surrogate CLIP model, it attains a mean zero-shot scene-classification attack success rate (ASR, the fraction of samples whose top-1 class changes) of 48.5% across five diverse CLIP backbones, far exceeding four IR-specific physical baselines (27.7--37.0%). Applied to six state-of-the-art VLMs, it cuts scene-classification accuracy by up to 38.2% relative, yet paradoxically makes some models more confident in their IR analysis, confabulating the perturbation as genuine thermal evidence such as temperature gradients and convection. Ablations show the airflow prior raises physical plausibility at no measurable cost to attack success. Together with a benchmark spanning eleven models and four tasks, these findings expose critical vulnerabilities in the rapidly expanding IR VLM ecosystem.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 39 of its 52 references that are in the map. First posted on arXiv 7 Jul 2026.

Builds on

39 of 52 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector19 Aug
  2. 2024Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks24 Nov
  3. 2023On Evaluating Adversarial Robustness of Large Vision-Language Models26 May
  4. 2022Towards Adversarial Attack on Vision-Language Pre-training Models19 Jun

Other references · 35

  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. 2013Intriguing properties of neural networkscited by 5,155
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  7. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  9. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  10. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,173
  11. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  12. 2016Practical Black-Box Attacks against Machine Learningcited by 903
23 more
  1. 2016Universal adversarial perturbationscited by 784
  2. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  3. 2017Adversarial Patchcited by 517
  4. 2023RemoteCLIP: A Vision Language Foundation Model for Remote Sensingcited by 363
  5. 2023GeoChat: Grounded Large Vision-Language Model for Remote Sensingcited by 328
  6. 2017Exploring Models and Data for Remote Sensing Image Caption Generationcited by 197
  7. 2023RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensingcited by 151
  8. 2023On the Adversarial Robustness of Multi-Modal Foundation Modelscited by 145
  9. 2023SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensingcited by 125
  10. 2023AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learningcited by 103
  11. 2024VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysiscited by 86
  12. 2022Exploring a Fine-Grained Multiscale Method for Cross-Modal Remote Sensing Image Retrievalcited by 77
  13. 2021Accelerating Atmospheric Turbulence Simulation via Learned Phase-to-Space Transformcited by 50
  14. 2022Infrared Invisible Clothing:Hiding from Infrared Detectors at Multiple Angles in Real Worldcited by 42
  15. 2023Physically Adversarial Infrared Patches with Learnable Shapes and Locationscited by 39
  16. 2021AdvHaze: Adversarial Haze Attackcited by 31
  17. 2022HOTCOLD Block: Fooling Thermal Infrared Detectors with a Novel Wearable Designcited by 27
  18. 2022Universal Adversarial Examples in Remote Sensing: Methodology and Benchmarkcited by 24
  19. 2022AI Security for Geoscience and Remote Sensing: Challenges and Future Trendscited by 23
  20. 2023Distracting Downpour: Adversarial Weather Attacks for Motion Estimationcited by 15
  21. 2023Adversarial Infrared Curves: An Attack on Infrared Pedestrian Detectors in the Physical Worldcited by 10
  22. 2025Generating Transferrable Adversarial Examples via Local Mixing and Logits Optimization for Remote Sensing Object Recognitioncited by 1
  23. 2026Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classificationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patch for Infrared Vision-Language Models
  2. 2026MonoIR-RS: Infrared Remote Sensing Vision-Language Learning with CLIP and VLM Adaptation
  3. 2026From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAG
  4. 2026GeoThreat: Transferable Targeted Adversarial Attacks on Large Vision-Language Models for Remote Sensing Image Interpretation
  5. 2026QR-Structured Thermal Triggers for Targeted Semantic Attacks on Infrared Vision-Language Models
  6. 2026FusionRS: A Large-Scale RGB-Infrared-Style Remote Sensing Dataset for Cross-Modal Vision-Language Learning
  7. 2026InfraQR: Edge-Placed QR-Inspired Structured Patch Attacks on Infrared Vision-Language Models
  8. 2025RGB-Th-Bench: A Dense benchmark for Visual-Thermal Understanding of Vision Language Models