InfraPatch: Cross-Task Targeted Grayscale Patch Attacks on Infrared-Adapted Vision-Language Models

• URL: http://arxiv.org/abs/2609.02233v1
• Date: Wed, 02 Sep 2026 07:42:27 GMT
• Title: InfraPatch: Cross-Task Targeted Grayscale Patch Attacks on Infrared-Adapted Vision-Language Models
• Abstract summary: Infrared vision-adaptive models (IR-VLMs) have emerged as a promising paradigm for multimodal perception under low-visibility conditions.<n>We propose InfraPatch, a framework for targeted digital grayscale patch attacks against IR-VLMs.
• Score: 9.310612317083928
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Infrared vision-language models (IR-VLMs) have emerged as a promising paradigm for multimodal perception under low-visibility conditions, yet their robustness to targeted adversarial attacks remains poorly understood. Existing adversarial patch methods mainly study RGB-based models or a single downstream task and do not characterize whether localized perturbations can induce an intended semantic target in IR-VLMs. We propose InfraPatch, a white-box, per-instance framework for targeted digital grayscale patch attacks against IR-VLMs. InfraPatch optimizes a compact single-channel patch within an approximately 5% local-area budget, combines proxy-guided placement with task-adaptive semantic objectives, and induces target behaviors in image classification, image captioning, and binary visual question answering. We evaluate ten infrared-adapted model variants on 300 synthetic infrared-style images generated by applying DiffV2IR to a fixed 30-category COCO subset, using clean-conditioned targeted success criteria. InfraPatch achieves targeted attack success rates from 86.00% to 100% across the ten variants. On CLIP and BLIP-2, proxy location search improves success by 6.67 and 10.33 percentage points over optimized random placement, respectively; LLaVA-1.5 remains saturated near 100% under both settings. Patch-area and objective ablations further expose substantial differences in vulnerability across architectures and task formats. These results show that small grayscale patches can inject chosen target semantics across IR-VLM families under a controlled digital threat model, motivating stronger robustness evaluation for infrared multimodal systems.

Related papers

• InfraQR: Edge-Placed QR-Inspired Structured Patch Attacks on Infrared Vision-Language Models [6.982777059279356]
  We present InfraQR, a QR-inspired structured patch attack for infrared vision-language models.<n>We evaluate it on infrared classification, caption transfer, and question-answer-aware visual question answering tasks.<n>Results show that infrared vision-language models remain vulnerable to structured edge-placed perturbations.
  arXiv  Detail & Related papers  (2026-07-08T11:28:15Z)
• Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patches for Infrared Vision-Language Models [21.429674567539607]
  Infrared vision-language models (IR-VLMs) have emerged as a promising paradigm for multimodal perception in low-visibility environments.<n>Existing adversarial patch methods are mainly designed for RGB-based models in closed-set settings.<n>We propose Universal Curved-Grid Patch (UCGP), a universal physical adversarial patch framework for IR-VLMs.
  arXiv  Detail & Related papers  (2026-04-03T15:42:55Z)
• Adversarial Patch Generation for Visual-Infrared Dense Prediction Tasks via Joint Position-Color Optimization [14.358458317718174]
  We propose a joint position-color optimization framework (AP-PCO) for generating adversarial patches in visual-infrared settings.<n>We introduce a crossmodal color adaptation strategy that constrains patch appearance according to infrared grayscale characteristics.<n> experiments on visual-infrared dense prediction tasks demonstrate that the proposed AP-PCO achieves consistently strong attack performance.
  arXiv  Detail & Related papers  (2026-02-27T19:26:17Z)
• When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models [81.7618160628979]
  Vision-Language-Action (VLA) models are vulnerable to adversarial attacks, yet universal and transferable attacks remain underexplored.<n>We introduce UPA-RFAS (Universal Patch Attack via Robust Feature, Attention, and Semantics), a unified framework that learns a single physical patch in a shared feature space.<n> Experiments across diverse VLA models, manipulation suites, and physical executions show that UPA-RFAS consistently transfers across models, tasks, and viewpoints.
  arXiv  Detail & Related papers  (2025-11-26T09:16:32Z)
• IrisNet: Infrared Image Status Awareness Meta Decoder for Infrared Small Targets Detection [92.56025546608699]
  IrisNet is a novel meta-learned framework that adapts detection strategies to the input infrared image status.<n>Our approach establishes a dynamic mapping between infrared image features and entire decoder parameters.<n> Experiments on NUDT-SIRST, NUAA-SIRST, and IRSTD-1K datasets demonstrate the superiority of our IrisNet.
  arXiv  Detail & Related papers  (2025-11-25T13:53:54Z)
• Targeted Physical Evasion Attacks in the Near-Infrared Domain [44.41293301858757]
  We propose a stealthy, and cost-effective attack to generate both targeted and untargeted infrared perturbations.<n>By projecting perturbations from a transparent film onto the target object with an off-the-shelf infrared flashlight, our approach is the first to reliably mount laser-free targeted attacks in the infrared domain.
  arXiv  Detail & Related papers  (2025-09-02T07:37:10Z)
• DISTA-Net: Dynamic Closely-Spaced Infrared Small Target Unmixing [55.366556355538954]
  We propose the Dynamic Iterative Shrinkage Thresholding Network (DISTA-Net), which reconceptualizes traditional sparse reconstruction within a dynamic framework.<n>DISTA-Net is the first deep learning model designed specifically for the unmixing of closely-spaced infrared small targets.<n>We have established the first open-source ecosystem to foster further research in this field.
  arXiv  Detail & Related papers  (2025-05-25T13:52:00Z)
• CDUPatch: Color-Driven Universal Adversarial Patch Attack for Dual-Modal Visible-Infrared Detectors [6.8163437709379835]
  Adversarial patches are widely used to evaluate the robustness of object detection systems in real-world scenarios.<n>We propose CDUPatch, a universal cross-modal patch attack against visible-infrared object detectors across scales, views, and scenarios.<n>By learning an optimal color distribution on the adversarial patch, we can manipulate its thermal response and generate an adversarial infrared texture.
  arXiv  Detail & Related papers  (2025-04-15T05:46:00Z)
• Multi-Domain Biometric Recognition using Body Embeddings [51.36007967653781]
  We show that body embeddings perform better than face embeddings in medium-wave infrared (MWIR) and long-wave infrared (LWIR) domains.<n>We leverage a vision transformer architecture to establish benchmark results on the IJB-MDF dataset.<n>We also show that finetuning a body model, pretrained exclusively on VIS data, with a simple combination of cross-entropy and triplet losses achieves state-of-the-art mAP scores.
  arXiv  Detail & Related papers  (2025-03-13T22:38:18Z)
• Towards Robust Infrared Small Target Detection: A Feature-Enhanced and Sensitivity-Tunable Framework [2.4810332733338623]
  We propose a feature-enhanced and sensitivity-tunable (FEST) framework, which is compatible with existing SIRST detection networks.<n>We show that our FEST framework can significantly enhance the performance of existing SIRST detection networks.<n> Notably, the multi-scale direction-aware network (MSDA-Net) equipped with the FEST framework won the first prize in the PRCV 2024 wide-area infrared small target detection competition.
  arXiv  Detail & Related papers  (2024-07-29T15:22:02Z)
• SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised Learning for Robust Infrared Small Target Detection [53.19618419772467]
  Single-frame infrared small target (SIRST) detection aims to recognize small targets from clutter backgrounds. With the development of Transformer, the scale of SIRST models is constantly increasing. With a rich diversity of infrared small target data, our algorithm significantly improves the model performance and convergence speed.
  arXiv  Detail & Related papers  (2024-03-08T16:14:54Z)
• SpirDet: Towards Efficient, Accurate and Lightweight Infrared Small Target Detector [60.42293239557962]
  We propose SpirDet, a novel approach for efficient detection of infrared small targets. We employ a new dual-branch sparse decoder to restore the feature map. Extensive experiments show that the proposed SpirDet significantly outperforms state-of-the-art models.
  arXiv  Detail & Related papers  (2024-02-08T05:06:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.