AirflowAttack: Thermal-Airflow Adversarial Perturbations against Infrared Remote-Sensing Vision-Language Models
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessAdversarial AttackSimilar Papers 제목 키워드 기반
Comprehensive Analysis of Thermal Dissipation in Lithium-Ion Battery Packs
Effective thermal management is critical for lithium-ion battery packs' safe and efficient operations, particularly in applications such as drones, where compact designs and varying airflow conditions present unique chal…
ManagementLearning-based Airflow Inertial Odometry for MAVs using Thermal Anemometers in a GPS and vision denied environment
This work demonstrates an airflow inertial based odometry system with multi-sensor data fusion, including thermal anemometer, IMU, ESC, and barometer. This goal is challenging because low-cost IMUs and barometers have si…
Universality, Robustness, and Detectability of Adversarial Perturbations under Adversarial Training
Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space. While adversarial training improves the robustness of classifiers…
Contributions of natural ventilation on thermal performance of alternative floor plan designs
During the earliest phase of architectural design process, practitioners after analyzing the client's design program, legal requirements, topographic constraints, and preferences synthesize these requirements into archit…
Defending Against Universal Perturbations With Shared Adversarial Training
Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space. While adversarial training improves the robustness of image class…
image-classificationImage ClassificationSemantic Segmentation